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

    Neuronpedia

    INDEX
    Explanations

    references to software development or programming tools

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

    code comments/copyright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.75
    󠁴
    -0.73
    featureID
    -0.72
     Roskov
    -0.71
    SharedCtor
    -0.71
    ArrowToggle
    -0.70
    localctx
    -0.70
     MainAxisSize
    -0.69
    verifyException
    -0.69
     الرياضيه
    -0.68
    POSITIVE LOGITS
     PhpStorm
    1.24
    inci
    0.40
     IntelliJ
    0.39
    Ram
    0.35
    Ent
    0.35
     Pet
    0.35
    bern
    0.33
     Ram
    0.33
     Conf
    0.32
    •
    0.32
    Act Density 0.000%

    No Known Activations