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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wipe
    -0.07
    وخ
    -0.07
    DlgItem
    -0.07
     nya
    -0.07
    ANGER
    -0.07
    formedURLException
    -0.06
    ettes
    -0.06
     בעזר
    -0.06
    疏导
    -0.06
    inputEmail
    -0.06
    POSITIVE LOGITS
    (serial
    0.08
    -report
    0.07
    .cpu
    0.07
    _head
    0.07
    天涯
    0.07
    รอบ
    0.07
    ')(
    0.07
     한
    0.07
     producto
    0.07
     배
    0.07
    Act Density 0.029%

    No Known Activations