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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fine
    -0.07
    ——
    -0.07
     Tahoe
    -0.07
     �
    -0.06
     Kỳ
    -0.06
    谈
    -0.06
     शत
    -0.06
    Ren
    -0.06
     Jenner
    -0.06
    Py
    -0.06
    POSITIVE LOGITS
    verbose
    0.07
    教授
    0.06
     formData
    0.06
    prof
    0.06
    compass
    0.06
    pill
    0.06
     piles
    0.06
     limiting
    0.06
     telecom
    0.06
     dumpsters
    0.06
    Act Density 0.003%

    No Known Activations