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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong emotions or reactions

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

    Adjectives describing something positive or negative

    np_acts-logits-general · gemini-2.0-flash

    strong adjectives and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.73
     vastaan
    -0.64
    ConstraintMaker
    -0.62
    Meaning
    -0.60
     consultato
    -0.60
    AndEndTag
    -0.60
    seamnă
    -0.60
     ejus
    -0.59
    LinkId
    -0.59
     enää
    -0.58
    POSITIVE LOGITS
     indeed
    1.01
    indeed
    0.75
    تقاوى
    0.63
     inderdaad
    0.63
     isn
    0.60
     honestly
    0.60
    ViewFeatures
    0.59
     watching
    0.59
     how
    0.57
     hearing
    0.57
    Act Density 0.187%

    No Known Activations