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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conclusions or judgments based on evidence

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

    palpably, notice, knowledge, see, manifest, knows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    接
    -0.28
     آم
    -0.28
     halfway
    -0.27
    Unknown
    -0.27
     priv
    -0.26
    がら
    -0.26
     thrown
    -0.26
     բ
    -0.26
     tentatively
    -0.26
     незавершена
    -0.26
    POSITIVE LOGITS
    AddTagHelper
    0.77
    SequentialGroup
    0.69
    evident
    0.66
    delwed
    0.66
    WebVitals
    0.65
    NameInMap
    0.64
    obvious
    0.63
     '\\;'
    0.63
    extAlignment
    0.61
     evidente
    0.60
    Act Density 0.151%

    No Known Activations