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

    Neuronpedia

    INDEX
    Explanations

    closing braces in code snippets

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

    setting values in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.70
     betweenstory
    -0.69
     Exactos
    -0.59
    addPreferredGap
    -0.57
     queſta
    -0.56
    tvguidetime
    -0.54
     ujednoznacz
    -0.52
    unknownFields
    -0.52
    səhifə
    -0.50
     indígen
    -0.50
    POSITIVE LOGITS
     libremente
    0.41
     vœ
    0.41
     expresa
    0.37
    GOTREF
    0.37
     librement
    0.35
    JsonPropertyName
    0.35
     descar
    0.35
     literario
    0.34
    ulgação
    0.33
     circunstan
    0.33
    Act Density 0.001%

    No Known Activations