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

    Neuronpedia

    INDEX
    Explanations

    phrases related to misinformation and its dissemination

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

    Follows common punctuation marks

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }$_
    -0.49
    Cancell
    -0.47
    waterproof
    -0.43
    Waterproof
    -0.43
    couvrir
    -0.42
     lining
    -0.42
    leun
    -0.42
    ITURE
    -0.41
     lupo
    -0.41
    huahua
    -0.41
    POSITIVE LOGITS
    PerformLayout
    0.61
    ActionCreators
    0.44
    تقاوى
    0.42
     typelib
    0.41
     تكبرها
    0.40
    évaluateur
    0.40
    CrossRef
    0.40
    PreExecute
    0.39
    RectangleBorder
    0.37
    awtextra
    0.36
    Act Density 1.673%

    No Known Activations