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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вор
    -0.07
    =M
    -0.07
    321
    -0.06
    frac
    -0.06
    Toast
    -0.06
    _Server
    -0.06
    ensation
    -0.06
     exemple
    -0.06
     harvest
    -0.06
    arsi
    -0.06
    POSITIVE LOGITS
    _depth
    0.07
     enfer
    0.07
    StartTime
    0.06
     مشک
    0.06
     farther
    0.06
     overwhel
    0.06
     Посилання
    0.06
     onstage
    0.06
     nguyện
    0.06
     psychic
    0.06
    Act Density 0.026%

    No Known Activations