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

    Neuronpedia

    INDEX
    Explanations

    words and punctuation associated with complaints and dissatisfaction

    oai_token-act-pair · gemini-2.0-flash

    nothing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incipient
    -0.50
     tartalomajánló
    -0.49
     mít
    -0.48
     Inters
    -0.46
    thétique
    -0.46
     Tiberius
    -0.45
     intermittent
    -0.44
    ंदीखरीदारी
    -0.44
    republik
    -0.44
    ære
    -0.43
    POSITIVE LOGITS
     nothing
    2.66
    nothing
    2.36
    Nothing
    2.30
     Nothing
    2.23
     NOTHING
    2.05
    NOTHING
    1.94
     nothin
    1.80
     rien
    1.73
     nada
    1.55
     ничего
    1.50
    Act Density 2.669%

    No Known Activations