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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structure elements

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

    code delimiter completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.57
    ⟬
    -0.49
    UnsafeEnabled
    -0.48
    //
    -0.47
    delwed
    -0.45
     waiver
    -0.42
    Cyfarwyddwr
    -0.41
    馳走
    -0.40
    JvmStatic
    -0.40
    veloper
    -0.40
    POSITIVE LOGITS
     referenties
    0.48
     worth
    0.47
    XmlAccessType
    0.47
    Worth
    0.40
    Referencies
    0.40
    NewReader
    0.40
     Vainqueur
    0.39
     Worth
    0.38
     становника
    0.37
     незавершена
    0.37
    Act Density 0.037%

    No Known Activations