Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific references to actions or changes in conditions related to people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    pronouns and auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seems
    -0.72
    Obvious
    -0.72
     says
    -0.69
     ovviamente
    -0.69
     Seems
    -0.68
     said
    -0.67
     natuurlijk
    -0.66
     obvious
    -0.66
     tentu
    -0.66
     menurut
    -0.65
    POSITIVE LOGITS
     indeed
    1.21
     efectivamente
    1.12
    RenderAtEndOf
    1.04
     للمعارف
    1.03
    indeed
    0.98
    ConstraintMaker
    0.98
     inderdaad
    0.96
     ligiloj
    0.94
    IntoConstraints
    0.88
     صوتيه
    0.88
    Act Density 1.494%

    No Known Activations