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

    Neuronpedia

    INDEX
    Explanations

    download

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \widgets
    -0.07
     FormsModule
    -0.06
    ो।
    -0.06
     atrocities
    -0.06
    наруж
    -0.06
    pix
    -0.06
     Enable
    -0.06
     {?}
    -0.06
    (et
    -0.06
    ит
    -0.06
    POSITIVE LOGITS
    ेहर
    0.07
     recycling
    0.06
     Pharmaceutical
    0.06
    enze
    0.06
    团
    0.06
    ском
    0.06
    يد
    0.06
    εδ
    0.06
    Young
    0.06
    rott
    0.06
    Act Density 0.011%

    No Known Activations