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

    Neuronpedia

    INDEX
    Explanations

    want

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PY
    -0.07
    irlines
    -0.06
     Siege
    -0.06
    Ren
    -0.06
     endangered
    -0.06
    _lower
    -0.06
     心
    -0.06
     Fiction
    -0.06
     airlines
    -0.06
    ch
    -0.06
    POSITIVE LOGITS
     perman
    0.07
    ịnh
    0.07
     SimpleDateFormat
    0.07
     QDom
    0.06
    .hw
    0.06
     Uk
    0.06
    Were
    0.06
    (jTextField
    0.06
     irm
    0.06
     接
    0.06
    Act Density 0.030%

    No Known Activations