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

    Neuronpedia

    INDEX
    Explanations

    def

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bezpieczeństwa
    -0.07
     XM
    -0.07
    fortunate
    -0.07
    _X
    -0.07
    _bn
    -0.07
     injust
    -0.07
    atte
    -0.07
    iny
    -0.07
     Entwicklung
    -0.07
     referencedColumnName
    -0.07
    POSITIVE LOGITS
     عمر
    0.08
    -sem
    0.07
    ][:
    0.07
     specialists
    0.07
    移到
    0.06
    gens
    0.06
     indoor
    0.06
     בשנה
    0.06
     откр
    0.06
     Sons
    0.06
    Act Density 0.001%

    No Known Activations