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

    Neuronpedia

    INDEX
    Explanations

    statements of personal expression and experiences

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

    First person pronouns followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    I want, I can, I know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     already
    -0.63
     Already
    -0.58
     quoque
    -0.56
    already
    -0.55
    Already
    -0.54
     also
    -0.53
     právě
    -0.53
     springfox
    -0.53
     juist
    -0.52
    Xna
    -0.51
    POSITIVE LOGITS
     ever
    1.09
     EVER
    0.87
     really
    0.80
     Really
    0.80
    Really
    0.77
     realmente
    0.74
     tartalomajánló
    0.73
     véritable
    0.72
    really
    0.72
     wirklich
    0.71
    Act Density 0.190%

    No Known Activations