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

    Neuronpedia

    INDEX
    Explanations

    punctuated dialogue and editorial comments

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

    closing punctuation followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.91
     HttpNotFound
    -0.90
     queſta
    -0.74
    DockStyle
    -0.73
    تقاوى
    -0.71
    ądze
    -0.71
    endphp
    -0.71
    rrggbb
    -0.69
    хьтан
    -0.69
     Савезне
    -0.69
    POSITIVE LOGITS
    J
    0.34
    ick
    0.33
    conf
    0.33
     
    0.33
    1
    0.32
    I
    0.32
    2
    0.31
    C
    0.31
    ainya
    0.31
    Simply
    0.31
    Act Density 0.002%

    No Known Activations