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

    Neuronpedia

    INDEX
    Explanations

    references to cultural norms and practices

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

    cultural norms and behaviors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputTagHelper
    -0.53
    navigationItem
    -0.42
    $_['
    -0.39
     FixedUpdate
    -0.38
    humanité
    -0.38
    dflare
    -0.36
     spéciaux
    -0.35
     mendes
    -0.35
     Migrate
    -0.35
     fest
    -0.35
    POSITIVE LOGITS
    posedge
    0.53
    تقاوى
    0.50
    istic
    0.45
    iac
    0.45
    iertos
    0.45
     gesloten
    0.45
    RTLR
    0.44
     kín
    0.44
    plo
    0.44
    MMM
    0.43
    Act Density 0.067%

    No Known Activations