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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology and correlations related to experimental results

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

    contrastive statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.50
     ErrIntOverflow
    -0.43
    saus
    -0.42
    ┐
    -0.39
    stoma
    -0.38
    getattr
    -0.38
    olph
    -0.38
     Attr
    -0.36
    اخت
    -0.36
     Canal
    -0.35
    POSITIVE LOGITS
    GOTREF
    0.57
     instead
    0.57
    instead
    0.52
     зато
    0.50
     revanche
    0.48
     nevertheless
    0.48
    倒是
    0.48
    WebVitals
    0.48
    卻
    0.47
    却是
    0.47
    Act Density 0.619%

    No Known Activations