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

    Neuronpedia

    INDEX
    Explanations

    statements or phrases that convey clarity and simplicity in explanations

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

    simple clear explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.42
     ligiloj
    -0.41
    Izvori
    -0.40
     Jezus
    -0.40
     pengend
    -0.39
     otomatig
    -0.39
    tranno
    -0.39
    ValueGeneration
    -0.37
    prüfung
    -0.37
     ilişk
    -0.37
    POSITIVE LOGITS
     propOrder
    0.67
    TRAILING
    0.54
     kasarigan
    0.46
    PerformLayout
    0.43
    簡単
    0.43
    Tembelea
    0.42
     cjs
    0.41
     obvious
    0.40
    Gambas
    0.39
    Familiar
    0.39
    Act Density 0.151%

    No Known Activations