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

    Neuronpedia

    INDEX
    Explanations

    terms related to attributes and error messages in code

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

    error message reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bland
    -0.35
     rocker
    -0.34
     tar
    -0.33
    [/
    -0.33
    fs
    -0.33
    Simply
    -0.32
    cco
    -0.32
    antar
    -0.31
     fas
    -0.31
     VIDEOTAPE
    -0.31
    POSITIVE LOGITS
     IEnumerator
    1.54
    IEnumerator
    1.34
     SafeMath
    0.84
     FormsModule
    0.82
    WriteAttribute
    0.79
    хь
    0.78
    featureID
    0.76
    SafeMath
    0.75
    PerformLayout
    0.74
    ValueStyle
    0.71
    Act Density 0.001%

    No Known Activations