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

    Neuronpedia

    INDEX
    Explanations

    design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <L
    -0.07
    ách
    -0.06
    χής
    -0.06
    \v
    -0.06
    -flight
    -0.06
    _RO
    -0.06
    chas
    -0.06
    _ROOT
    -0.06
    ασία
    -0.06
    مند
    -0.06
    POSITIVE LOGITS
     Mag
    0.08
     الات
    0.06
    -established
    0.06
     شور
    0.06
     Superman
    0.06
     ----------------------------------------------------------------------------------------------------------------
    0.06
     brewed
    0.06
    �
    0.06
    esModule
    0.06
     edited
    0.06
    Act Density 0.017%

    No Known Activations