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

    Neuronpedia

    INDEX
    Explanations

    art

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abundance
    -0.07
     situated
    -0.06
    алі
    -0.06
    implementation
    -0.06
    _integral
    -0.06
    extern
    -0.06
     Cooling
    -0.06
    Detector
    -0.06
    oriasis
    -0.06
     impatient
    -0.06
    POSITIVE LOGITS
    .UseFont
    0.06
    اسات
    0.06
     discredit
    0.06
     rewind
    0.06
    bel
    0.06
    ultz
    0.06
    ประม
    0.06
     çıkart
    0.06
    父
    0.06
    atti
    0.06
    Act Density 0.007%

    No Known Activations