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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -is
    -0.06
    .grad
    -0.06
    í
    -0.06
     Encoding
    -0.06
    ぐ
    -0.06
    .bias
    -0.06
    -answer
    -0.06
     fue
    -0.06
     Nazis
    -0.06
    _width
    -0.06
    POSITIVE LOGITS
    (inflater
    0.07
    omanip
    0.07
    Emb
    0.06
    ERRUPT
    0.06
     úspě
    0.06
     العربي
    0.06
    delivr
    0.06
    reeting
    0.06
    (hours
    0.06
    منی
    0.06
    Act Density 0.022%

    No Known Activations