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

    Neuronpedia

    INDEX
    Explanations

    Ben

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cites
    -0.07
    _Number
    -0.07
    _sym
    -0.07
    -paper
    -0.06
    Entropy
    -0.06
     comerc
    -0.06
    (formData
    -0.06
    ứng
    -0.06
     Chamber
    -0.06
     wilderness
    -0.06
    POSITIVE LOGITS
     instagram
    0.06
    ExceptionHandler
    0.06
    ΙΚΟ
    0.06
     gunman
    0.06
    <int
    0.06
    งต
    0.06
    ‌ای
    0.06
    =__
    0.06
    [field
    0.06
    LENGTH
    0.06
    Act Density 0.003%

    No Known Activations