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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =t
    -0.08
     وك
    -0.07
    izando
    -0.07
     TICK
    -0.07
    ㉢
    -0.06
    )b
    -0.06
    e
    -0.06
    .est
    -0.06
    invest
    -0.06
    吐槽
    -0.06
    POSITIVE LOGITS
    _document
    0.07
    קוב
    0.07
    kür
    0.07
    .styles
    0.07
    ViewChild
    0.07
    Contours
    0.07
    后果
    0.07
     Quiz
    0.07
     śmier
    0.06
    .Cryptography
    0.06
    Act Density 0.004%

    No Known Activations