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

    Neuronpedia

    INDEX
    Explanations

    configuration and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Flag
    0.80
    стного
    0.75
     Primitive
    0.74
     Hal
    0.72
    iker
    0.72
    Elementary
    0.72
     Flag
    0.71
    Algorithm
    0.71
    Princip
    0.70
     Rehabilitation
    0.70
    POSITIVE LOGITS
     ssl
    0.94
     дов
    0.93
    ssl
    0.89
    閑
    0.84
     дол
    0.84
    dotenv
    0.83
    SSL
    0.82
     proof
    0.79
     nuove
    0.77
     comprimento
    0.77
    Act Density 0.000%

    No Known Activations