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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, parentheses, and formatting symbols

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adentro
    -0.28
    holdet
    -0.28
    II
    -0.27
     senhora
    -0.27
     Inscrivez
    -0.27
     coucher
    -0.27
     costes
    -0.26
    还不
    -0.26
    akaian
    -0.26
     refroidissement
    -0.25
    POSITIVE LOGITS
     nakalista
    0.83
    UnsafeEnabled
    0.78
    طلحات
    0.76
    بوابة
    0.73
    webElementXpaths
    0.72
    WebElementEntity
    0.69
     transfieras
    0.67
     Infórmanos
    0.67
    niſſe
    0.66
     kasarigan
    0.66
    Act Density 0.010%

    No Known Activations