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

    Neuronpedia

    INDEX
    Explanations

    code, steps, and parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रतिनिधित्व
    0.84
    ("
    0.82
    典型的
    0.81
    (=
    0.80
    (
    0.79
     seguente
    0.79
     (_,
    0.78
    identical
    0.76
    ($_
    0.76
    （
    0.75
    POSITIVE LOGITS
     easier
    0.85
     parts
    0.82
     terutama
    0.76
     difficult
    0.75
     especially
    0.74
    等人
    0.73
     niektó
    0.73
     או
    0.73
    更多
    0.73
     areas
    0.71
    Act Density 0.022%

    No Known Activations