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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    contre
    -0.07
    ского
    -0.07
    owie
    -0.07
    Modules
    -0.06
    eroon
    -0.06
    IfNeeded
    -0.06
     haber
    -0.06
    /(?
    -0.06
    ,w
    -0.06
    バ
    -0.06
    POSITIVE LOGITS
    ปก
    0.07
    _CPU
    0.06
     dads
    0.06
    .Multiline
    0.06
    usion
    0.06
    .calculate
    0.06
    Cancel
    0.06
     maduras
    0.06
     diện
    0.06
     Cindy
    0.06
    Act Density 0.076%

    No Known Activations