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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    _NO
    -0.07
     realistically
    -0.07
    .TRAN
    -0.07
    _ar
    -0.06
     다음과
    -0.06
    tom
    -0.06
    ॉक
    -0.06
     остров
    -0.06
     COPYING
    -0.06
    POSITIVE LOGITS
    กำหนด
    0.07
    。但
    0.06
    topic
    0.06
    -shirts
    0.06
     ।
    0.06
    debian
    0.06
    ubit
    0.06
     Lazy
    0.06
    ”。
    0.06
    errorMessage
    0.06
    Act Density 0.039%

    No Known Activations