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

    Neuronpedia

    INDEX
    Explanations

    references to things that are unspecified or not clearly identified

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    unknown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.54
    posedge
    -0.51
    +#+
    -0.47
    ArgumentParser
    -0.47
    deutig
    -0.46
     proprement
    -0.44
    こうして
    -0.44
    VideoCapture
    -0.43
    RetentionPolicy
    -0.42
    Попис
    -0.42
    POSITIVE LOGITS
     unknown
    1.39
     Unknown
    1.38
    Unknown
    1.27
    unknown
    1.25
     UNKNOWN
    1.16
     unknowns
    1.07
     неизвест
    0.99
     unknow
    0.96
    UNKNOWN
    0.95
     desconocido
    0.93
    Act Density 0.027%

    No Known Activations