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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ajor
    -0.08
     wk
    -0.08
    title
    -0.06
     thế
    -0.06
    ová
    -0.06
     indictment
    -0.06
    Thread
    -0.06
    ющими
    -0.06
     Hammer
    -0.06
     Tian
    -0.06
    POSITIVE LOGITS
    ginas
    0.06
    -config
    0.06
    asco
    0.06
     nez
    0.06
    概
    0.06
    狼
    0.06
    ainting
    0.06
    _coupon
    0.06
    èm
    0.06
     entrada
    0.06
    Act Density 0.016%

    No Known Activations