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

    Neuronpedia

    INDEX
    Explanations

    programming/technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appointment
    -0.06
     smiling
    -0.06
     nowrap
    -0.06
    <Expression
    -0.06
    切
    -0.06
     working
    -0.06
     Appointment
    -0.06
     FFT
    -0.06
    _secs
    -0.05
     मश
    -0.05
    POSITIVE LOGITS
     Spielberg
    0.08
     خود
    0.07
    ､:
    0.07
    inha
    0.07
    ,current
    0.06
    liğinin
    0.06
    /pol
    0.06
     funkce
    0.06
     زنان
    0.06
    ной
    0.06
    Act Density 0.362%

    No Known Activations