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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks indicating structure or formatting in text

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

    alternate. some

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     justiça
    -0.40
     دیکھیے
    -0.40
    __":
    -0.39
     gravidez
    -0.35
    addington
    -0.35
    íritu
    -0.35
    Spann
    -0.34
    Schicken
    -0.34
     Gep
    -0.33
    mogat
    -0.33
    POSITIVE LOGITS
     alternative
    2.03
     Alternative
    1.84
     alternate
    1.83
    alternative
    1.79
    Alternative
    1.77
     ALTERNATIVE
    1.70
     ALTERN
    1.69
     altern
    1.68
     alternatives
    1.66
     Alternate
    1.65
    Act Density 0.019%

    No Known Activations