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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ắn
    -0.06
    हर
    -0.06
    ihn
    -0.06
     posts
    -0.06
    "></
    -0.06
    >:
    -0.06
     بهره
    -0.06
    KeyEvent
    -0.06
    slashes
    -0.06
    형
    -0.06
    POSITIVE LOGITS
     kry
    0.06
     Indones
    0.06
     дер
    0.06
    [arg
    0.06
     disproportionately
    0.06
    smart
    0.06
     vais
    0.06
    /********************************************************************************
    0.06
    357
    0.06
     [])
    0.06
    Act Density 0.014%

    No Known Activations