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

    Neuronpedia

    INDEX
    Explanations

    references to personal identity or self-description

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

    "a" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    a [descriptor]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     démocr
    -0.70
     Púb
    -0.68
     educativas
    -0.66
     educativos
    -0.65
    koľvek
    -0.63
     motivadoras
    -0.61
     natale
    -0.60
     rerum
    -0.60
     maschile
    -0.60
     liknande
    -0.59
    POSITIVE LOGITS
     optim
    0.67
     college
    0.60
     human
    0.58
     professional
    0.54
     proud
    0.53
     Hoek
    0.52
     cyn
    0.51
     hardcore
    0.51
     true
    0.50
    ciaio
    0.50
    Act Density 0.302%

    No Known Activations