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

    Neuronpedia

    INDEX
    Explanations

    numeric values and references to scientific articles

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

    URLs with a DOI identifier

    np_acts-logits-general · gemini-2.0-flash

    DOIs and academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carbone
    -0.46
    anja
    -0.45
    ához
    -0.43
     رأس
    -0.43
     ιδ
    -0.43
     levantó
    -0.43
    ضب
    -0.42
    nonatomic
    -0.42
     relativo
    -0.42
    anilla
    -0.42
    POSITIVE LOGITS
    DataAnnotations
    0.81
     ISNI
    0.81
     الحره
    0.76
     InputDecoration
    0.71
     Himo
    0.68
     AssemblyCulture
    0.67
    aarrggbb
    0.66
    ScopeManager
    0.66
     SwitchCompat
    0.63
    ResumeLayout
    0.63
    Act Density 0.204%

    No Known Activations