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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making decisions

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

    Prepositions and particles

    np_acts-logits-general · gemini-2.0-flash

    prepositions or endpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.71
    )"),
    -0.63
    MessageOf
    -0.62
    "]}
    -0.58
    }")]
    -0.56
     regia
    -0.56
    segue
    -0.54
    ую
    -0.54
    ()");
    -0.54
    ViewFeatures
    -0.53
    POSITIVE LOGITS
    tvguidetime
    0.66
     فريبيس
    0.59
     who
    0.55
    TestingModule
    0.53
    dollis
    0.52
     NUKAT
    0.52
    who
    0.51
    ConstraintMaker
    0.50
    IntoConstraints
    0.50
    তথ্যসূত্র
    0.49
    Act Density 0.190%

    No Known Activations