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

    Neuronpedia

    INDEX
    Explanations

    coercion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phishing
    -0.07
     Merk
    -0.07
    _FEATURE
    -0.06
    /wait
    -0.06
     ************************************************
    -0.06
     maxLength
    -0.06
    wr
    -0.06
     Pager
    -0.06
     nowhere
    -0.06
     کاهش
    -0.06
    POSITIVE LOGITS
    ทย
    0.06
     prompts
    0.06
     zaw
    0.06
    搬
    0.06
     Latin
    0.06
    ùi
    0.06
     blobs
    0.06
    .Result
    0.06
    lep
    0.06
    .ones
    0.06
    Act Density 0.042%

    No Known Activations