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

    Neuronpedia

    INDEX
    Explanations

    .junit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Promise
    -0.07
    smouth
    -0.07
     χρη
    -0.06
     Зак
    -0.06
    .scope
    -0.06
    Duration
    -0.06
    ocket
    -0.06
     Memphis
    -0.06
    onth
    -0.06
    بین
    -0.06
    POSITIVE LOGITS
    궁
    0.07
    -character
    0.06
    �
    0.06
    erap
    0.06
     ├
    0.06
     grew
    0.06
     immediate
    0.06
    tod
    0.06
    medi
    0.06
     -----
    0.06
    Act Density 0.001%

    No Known Activations