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

    Neuronpedia

    INDEX
    Explanations

    probability, possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    озвращает
    -0.07
    AdapterFactory
    -0.07
     signal
    -0.06
    patient
    -0.06
     Loop
    -0.06
     Return
    -0.06
     Connie
    -0.06
     Spectrum
    -0.06
    orrow
    -0.06
     correlations
    -0.06
    POSITIVE LOGITS
    _SCHEDULE
    0.08
    _COUNT
    0.07
     slated
    0.07
    _chance
    0.06
     MÜ
    0.06
    ался
    0.06
     searchable
    0.06
    ortho
    0.06
    xmin
    0.06
     TASK
    0.06
    Act Density 0.017%

    No Known Activations