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

    Neuronpedia

    INDEX
    Explanations

    grateful for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒊕
    1.29
    垶
    1.24
    <unused741>
    1.23
    sbParams
    1.22
    萺
    1.20
     stateMutability
    1.19
    곞
    1.18
    𒀉
    1.18
     scammers
    1.18
     egos
    1.18
    POSITIVE LOGITS
     (
    0.86
     min
    0.85
     via
    0.75
     der
    0.73
     T
    0.73
     ()
    0.72
     *
    0.72
    <blockquote>
    0.72
     super
    0.70
     functional
    0.69
    Act Density 0.007%

    No Known Activations