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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating high levels of urgency or critical importance

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

    Punctuation, symbols, and fragments

    np_acts-logits-general · gemini-2.0-flash

    code, punctuation, and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.76
    IsMutable
    -0.59
    InstrumentedTest
    -0.59
     PackageManager
    -0.58
    openzeppelin
    -0.56
     onAnimation
    -0.55
    ="@+
    -0.54
    detectChanges
    -0.53
    Obec
    -0.53
    PhysRevD
    -0.53
    POSITIVE LOGITS
    "])
    0.72
    "]).
    0.57
    '])
    0.57
     Theſe
    0.56
    ].)
    0.56
    ."</
    0.55
    Merken
    0.55
    "]))
    0.54
    互联网档案馆
    0.54
     Grecs
    0.54
    Act Density 0.295%

    No Known Activations