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

    Neuronpedia

    INDEX
    Explanations

    selection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    řel
    -0.07
    _UP
    -0.07
     offspring
    -0.06
    _Char
    -0.06
    act
    -0.06
    Все
    -0.06
    Laura
    -0.06
    那
    -0.06
    Owned
    -0.06
    .look
    -0.06
    POSITIVE LOGITS
     eater
    0.07
     tq
    0.07
    graded
    0.06
     respective
    0.06
     suspicion
    0.06
     будут
    0.06
     discretionary
    0.06
    resume
    0.06
    :normal
    0.06
    ↵    ↵
    0.06
    Act Density 0.011%

    No Known Activations