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

    Neuronpedia

    INDEX
    Explanations

    dating profiles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Licensing
    -0.06
    _COMPLETED
    -0.06
    _SENT
    -0.06
    .offset
    -0.06
    Hidden
    -0.06
     bound
    -0.06
     Men
    -0.06
     audible
    -0.06
     hangs
    -0.06
    ////////////////////////////////////////////////////////
    -0.06
    POSITIVE LOGITS
     veterinarian
    0.07
     attend
    0.07
     образом
    0.07
    IRC
    0.07
     anlay
    0.06
    像是
    0.06
    нь
    0.06
    bron
    0.06
    eci
    0.06
    nummer
    0.06
    Act Density 0.081%

    No Known Activations