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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of doubt

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

    don't think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    󠁿
    -0.58
    s
    -0.51
    存于互联网档案馆
    -0.51
     Berry
    -0.44
     }^{*}$
    -0.41
    ria
    -0.41
    y
    -0.40
    Berry
    -0.40
     apiKey
    -0.40
    й
    -0.40
    POSITIVE LOGITS
    tvguidetime
    0.67
     ProtoMessage
    0.61
     Bewußt
    0.60
     ainfi
    0.60
     própri
    0.59
     desmotivaciones
    0.59
    pecabe
    0.58
     przec
    0.58
     للمعارف
    0.57
     Verſ
    0.57
    Act Density 0.007%

    No Known Activations