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

    Neuronpedia

    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SQ
    -0.07
     Durham
    -0.07
    ait
    -0.07
    .values
    -0.07
    .Left
    -0.07
    strftime
    -0.06
    .Marker
    -0.06
     Lunar
    -0.06
    _lm
    -0.06
    ôte
    -0.06
    POSITIVE LOGITS
    ermen
    0.06
     viện
    0.06
     WARNING
    0.06
     इतन
    0.06
     dept
    0.06
     mama
    0.06
    (EFFECT
    0.06
    ержав
    0.06
     پیشنهاد
    0.06
    евид
    0.06
    Act Density 0.003%

    No Known Activations