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

    Neuronpedia

    INDEX
    Explanations

    abbreviations for research terminology

    oai_token-act-pair · gemini-2.0-flash

    Code/technical documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hematical
    -0.68
     فريبيس
    -0.67
    expandindo
    -0.64
    elfare
    -0.62
     lisäksi
    -0.60
    ourite
    -0.60
    arranty
    -0.59
    ofold
    -0.57
    tionally
    -0.57
    antism
    -0.57
    POSITIVE LOGITS
    +#+#
    0.70
     createSprite
    0.60
    QRect
    0.51
    InitVars
    0.51
    Parcelize
    0.49
     getItemCount
    0.49
     createSlice
    0.46
    batore
    0.45
    oaks
    0.44
    LookAnd
    0.44
    Act Density 1.038%

    No Known Activations