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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming and coding structure

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

    code and markup syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    -0.33
    ね
    -0.33
    ukum
    -0.33
    g
    -0.33
    unt
    -0.31
    A
    -0.31
    当
    -0.31
    P
    -0.31
    主
    -0.30
    re
    -0.30
    POSITIVE LOGITS
     autorytatywna
    0.84
     الرياضيه
    0.83
    دانشنامهٔ
    0.73
     Wiktionnaire
    0.71
     auroit
    0.71
     abstrato
    0.68
     utafitiHapana
    0.68
     ligiloj
    0.67
    Datuak
    0.67
    <unused3>
    0.66
    Act Density 0.002%

    No Known Activations