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

    Neuronpedia

    INDEX
    Explanations

    negative statements or expressions of reluctance

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

    do not / cannot + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Signalez
    -0.69
    providedIn
    -0.60
     MainAxisSize
    -0.59
    uxxxx
    -0.58
     незавершена
    -0.56
    #+#
    -0.56
     kasarigan
    -0.55
     HttpNotFound
    -0.54
     autorytatywna
    -0.53
    ➟
    -0.53
    POSITIVE LOGITS
     ſind
    0.38
     Anſ
    0.34
     Inscrivez
    0.34
     speaker
    0.33
     bens
    0.32
    (!__
    0.32
    アナ
    0.32
     speakers
    0.32
     Puck
    0.31
    そうで
    0.31
    Act Density 0.030%

    No Known Activations