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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their surrounding context, particularly dashes and parentheses

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

    capitalized names and organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.48
    
    -0.46
     resourceCulture
    -0.45
    setVerticalGroup
    -0.44
    🥗
    -0.42
    oader
    -0.41
    
    -0.40
     Hilo
    -0.40
    Transkript
    -0.39
    üyada
    -0.38
    POSITIVE LOGITS
     насељу
    0.71
    Hozzáférés
    0.53
     کیلوم
    0.49
     poveznice
    0.46
    thâu
    0.44
     znaj
    0.42
    anthemum
    0.42
    annica
    0.41
    MENAFN
    0.41
    dialement
    0.41
    Act Density 0.010%

    No Known Activations