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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weit
    -0.08
    .sol
    -0.07
     Lithuania
    -0.07
    _BAD
    -0.07
    .spark
    -0.06
     Sul
    -0.06
     вони
    -0.06
    .Timeout
    -0.06
     ماد
    -0.06
     frontal
    -0.06
    POSITIVE LOGITS
     nghiệp
    0.07
    Code
    0.06
    Pr
    0.06
    support
    0.06
    've
    0.06
    patible
    0.06
     Call
    0.06
    启
    0.06
    ерина
    0.06
    151
    0.06
    Act Density 0.123%

    No Known Activations