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

    Neuronpedia

    INDEX
    Explanations

    software packages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     citizens
    -0.07
     никто
    -0.07
    .AspNet
    -0.07
     maiden
    -0.07
    _mail
    -0.06
     поэтому
    -0.06
     resilient
    -0.06
    -catching
    -0.06
     traf
    -0.06
     hacer
    -0.06
    POSITIVE LOGITS
    eger
    0.07
     pak
    0.07
     double
    0.06
     通
    0.06
    double
    0.06
     Double
    0.06
     의
    0.06
    Emitter
    0.06
     soğ
    0.06
    ayscale
    0.06
    Act Density 0.000%

    No Known Activations