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

    Neuronpedia

    INDEX
    Explanations

    dates and numerical references in text

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

    speeches, events, and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.40
     lèvres
    -0.39
    glLoadIdentity
    -0.38
    umbent
    -0.38
     öffentliche
    -0.38
     fronte
    -0.36
    JMenu
    -0.36
    basan
    -0.36
     dapur
    -0.35
     elástica
    -0.35
    POSITIVE LOGITS
     defaultstate
    0.53
    Kick
    0.50
    发表于
    0.50
    openzeppelin
    0.49
    kick
    0.49
    pushFollow
    0.47
    MemoryWarning
    0.46
     Kick
    0.45
    ScopeManager
    0.45
    PYX
    0.45
    Act Density 0.027%

    No Known Activations