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

    Neuronpedia

    INDEX
    Explanations

    references to documentation or API specifications

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

    doc comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſind
    -0.62
    QMetaType
    -0.54
    delwed
    -0.52
    zzleHttp
    -0.49
    ementara
    -0.47
    Spolja
    -0.47
    ństw
    -0.45
     ſeine
    -0.44
     myſelf
    -0.44
     ]];
    -0.44
    POSITIVE LOGITS
    doc
    3.39
     doc
    2.31
    Doc
    2.05
     Doc
    1.89
    DOC
    1.88
     DOC
    1.52
    docs
    1.43
     docs
    1.42
    Docs
    1.38
     Docs
    1.30
    Act Density 0.007%

    No Known Activations