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

    Neuronpedia

    INDEX
    Explanations

    ø

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     often
    -0.07
     cuent
    -0.07
    _languages
    -0.07
     cursed
    -0.07
     chang
    -0.07
     mujeres
    -0.07
    .date
    -0.07
     backward
    -0.07
    /x
    -0.07
     borders
    -0.07
    POSITIVE LOGITS
    ToAdd
    0.06
     CNBC
    0.06
    abcdefgh
    0.06
     منطقة
    0.06
     Gibson
    0.06
     Gür
    0.06
     CLIIIK
    0.06
    .fromLTRB
    0.06
    .SetFloat
    0.06
     Abd
    0.06
    Act Density 0.003%

    No Known Activations