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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to material properties and engineering processes

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

    divergent beliefs and directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kesha
    -0.41
     intStringLen
    -0.40
    enumerable
    -0.35
    -0.35
     Stellung
    -0.35
    enheim
    -0.35
     Panto
    -0.34
    FieldDescriptor
    -0.34
    ppé
    -0.34
    rote
    -0.33
    POSITIVE LOGITS
    AutoScaleMode
    0.40
    GeneratedCode
    0.40
     Roskov
    0.40
    oredCriteria
    0.40
    aarrggbb
    0.39
    Incompatible
    0.39
    تقاوى
    0.38
     Incompatible
    0.38
     obiettivi
    0.37
     mismatch
    0.37
    Act Density 0.118%

    No Known Activations