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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uninsured
    -0.07
    useum
    -0.06
    热爱
    -0.06
    CCA
    -0.06
    -editor
    -0.06
     drawer
    -0.06
     private
    -0.06
    acio
    -0.06
    .Err
    -0.06
     doctor
    -0.06
    POSITIVE LOGITS
     *)(
    0.07
    升降
    0.07
    bezpieczeńst
    0.07
    _encoding
    0.07
    plots
    0.07
    Calls
    0.07
     חודשים
    0.07
     Sudoku
    0.06
    >")
    0.06
     *"
    0.06
    Act Density 0.000%

    No Known Activations