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

    Neuronpedia

    INDEX
    Explanations

    opposing sides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     condemned
    -0.07
     entertained
    -0.07
     phased
    -0.06
     Gerard
    -0.06
     Electricity
    -0.06
    mailto
    -0.06
    лін
    -0.06
     suspects
    -0.06
     să
    -0.06
     somehow
    -0.06
    POSITIVE LOGITS
    ısız
    0.07
    _eta
    0.06
    �
    0.06
     sitio
    0.06
    izontal
    0.06
    -enh
    0.06
    .Pin
    0.06
    แป
    0.06
    CRET
    0.06
    duc
    0.06
    Act Density 0.112%

    No Known Activations