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

    Neuronpedia

    INDEX
    Explanations

    fig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boat
    -0.08
    shr
    -0.07
     Put
    -0.07
     showers
    -0.07
    Solar
    -0.07
     HAPP
    -0.06
    &lt
    -0.06
    unused
    -0.06
     sl
    -0.06
    Cou
    -0.06
    POSITIVE LOGITS
     wp
    0.06
    (AP
    0.06
    ="$(
    0.06
    oxetine
    0.06
    _staff
    0.06
    }*/↵↵
    0.06
    etrain
    0.06
    _Msk
    0.06
     filename
    0.06
    ICLE
    0.06
    Act Density 0.004%

    No Known Activations