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

    Neuronpedia

    INDEX
    Explanations

    punctuation and exclamatory expressions in text

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

    Code, symbols, and unusual punctuation

    np_acts-logits-general · gemini-2.0-flash

    positive sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.84
    MfG
    -0.84
    łbym
    -0.78
     Efq
    -0.78
     $_"
    -0.78
    นะครับ
    -0.77
    Gruß
    -0.76
     Daß
    -0.75
     IBRARY
    -0.75
    urther
    -0.74
    POSITIVE LOGITS
     LOVE
    0.82
     xoxo
    0.78
     LOVED
    0.76
    LOVE
    0.72
    xoxo
    0.71
     súper
    0.68
     hubby
    0.67
    Obrigada
    0.66
     gorgeous
    0.64
    xo
    0.63
    Act Density 0.150%

    No Known Activations