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

    Neuronpedia

    INDEX
    Explanations

    Code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /test
    -0.07
     related
    -0.07
    -elect
    -0.07
     Production
    -0.06
    ическое
    -0.06
    -but
    -0.06
     TEST
    -0.06
    uclear
    -0.06
     tribe
    -0.06
     bodies
    -0.06
    POSITIVE LOGITS
    NSSet
    0.08
    .ConnectionStrings
    0.06
    対応
    0.06
     начина
    0.06
     Sgt
    0.06
    (hex
    0.06
    ’B
    0.06
     sonu
    0.06
    ennis
    0.06
     Carrie
    0.06
    Act Density 0.249%

    No Known Activations