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

    Neuronpedia

    INDEX
    Explanations

    definite articles and other contextually significant terms that emphasize specificity or repetition

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

    a lot of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.63
    providedIn
    -0.61
     chi̍t
    -0.59
     myſelf
    -0.59
     faſt
    -0.59
     itſelf
    -0.53
     autorytatywna
    -0.52
     bogotá
    -0.51
    WebElementEntity
    -0.51
    ]")]
    -0.50
    POSITIVE LOGITS
     plupart
    0.46
    OfThe
    0.40
     Многие
    0.38
     flesta
    0.37
     majorité
    0.37
     principali
    0.36
     lutter
    0.36
     niektórych
    0.36
     большинство
    0.35
    こち
    0.35
    Act Density 0.016%

    No Known Activations