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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    可以使
    -0.08
    Consulta
    -0.07
    싯
    -0.07
    脖
    -0.07
    .Pin
    -0.07
    4
    -0.07
     HELP
    -0.07
     INV
    -0.07
    asd
    -0.07
    吖
    -0.07
    POSITIVE LOGITS
     $#
    0.07
    .sulake
    0.07
    ㎿
    0.06
    Bindable
    0.06
    ჻
    0.06
     Fra
    0.06
     Same
    0.06
     Devin
    0.06
    .UNRELATED
    0.06
    뎐
    0.06
    Act Density 0.002%

    No Known Activations