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

    Neuronpedia

    INDEX
    Explanations

    Initials and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _nh
    -0.08
    =find
    -0.07
    _discount
    -0.07
     Merch
    -0.06
    %↵
    -0.06
    ących
    -0.06
    ’ex
    -0.06
     ISPs
    -0.06
    絕
    -0.06
    ķ
    -0.06
    POSITIVE LOGITS
    .LayoutInflater
    0.08
    DBG
    0.07
    历时
    0.07
     cast
    0.07
    义
    0.07
     medio
    0.07
     Moment
    0.06
    ']].
    0.06
     Pass
    0.06
    vfs
    0.06
    Act Density 0.131%

    No Known Activations