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

    Neuronpedia

    INDEX
    Explanations

    say "( word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ķ
    -0.08
    皖
    -0.07
     Celsius
    -0.07
    �
    -0.07
    웡
    -0.07
    .Screen
    -0.06
    茁
    -0.06
     이상
    -0.06
     blood
    -0.06
    Marg
    -0.06
    POSITIVE LOGITS
    .getHeight
    0.08
    History
    0.08
    𖥨
    0.07
    altet
    0.07
    .getParent
    0.07
    -NLS
    0.07
    ⼿
    0.07
    �
    0.07
    _processing
    0.07
    stitute
    0.07
    Act Density 0.002%

    No Known Activations