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

    Neuronpedia

    INDEX
    Explanations

    initialization or first code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Internet
    0.52
    TE
    0.50
     ocurre
    0.47
    Time
    0.45
    ạm
    0.43
    -
    0.43
     Internet
    0.42
    鏂
    0.42
     ocorre
    0.42
    RE
    0.42
    POSITIVE LOGITS
    ਰ
    0.49
    ого
    0.47
     animaux
    0.46
     summaries
    0.45
     nationalists
    0.45
     somatic
    0.44
     종합
    0.44
    샀
    0.44
    ാർ
    0.44
     heuristics
    0.44
    Act Density 0.000%

    No Known Activations