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

    Neuronpedia

    INDEX
    Explanations

    table formatting with dashes

    oai_token-act-pair · gemini-2.0-flash

    Section dividers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.99
    -
    -0.55
    H
    -0.53
    U
    -0.47
    L
    -0.47
    y
    -0.45
    (
    -0.45
     nõ
    -0.45
    com
    -0.45
    my
    -0.44
    POSITIVE LOGITS
    EDEFAULT
    0.88
    HomeAsUpEnabled
    0.69
    0.69
     CascadeType
    0.68
     autorytatywna
    0.68
    IVEREF
    0.66
    tonsoft
    0.65
    enumii
    0.64
    doctype
    0.64
    AnchorStyles
    0.63
    Act Density 18.106%

    No Known Activations