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

    Neuronpedia

    INDEX
    Explanations

    988 crisis lifeline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.38
    /
    0.33
    USA
    0.28
    дання
    0.28
    ABC
    0.27
     M
    0.25
     P
    0.25
     and
    0.25
    тал
    0.25
    P
    0.25
    POSITIVE LOGITS
     iterable
    0.30
     dimensionless
    0.29
     multivalued
    0.28
     MediaQuery
    0.28
    蛞
    0.28
     mutating
    0.27
    rvGroup
    0.27
     fermion
    0.26
     mutable
    0.25
     arousal
    0.25
    Act Density 0.096%

    No Known Activations