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

    Neuronpedia

    INDEX
    Explanations

    foreign and connecting words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Subscribe
    0.66
    unsubscribe
    0.66
     Archives
    0.65
     Indices
    0.65
     Indexes
    0.65
     Translate
    0.64
    ünü
    0.63
    把握
    0.63
    Translate
    0.63
    જબ
    0.63
    POSITIVE LOGITS
    蚊
    0.63
     pronoun
    0.61
     airtight
    0.61
    otically
    0.60
     juguete
    0.60
     경우에는
    0.60
    ilateral
    0.59
    ordination
    0.58
    త్స
    0.57
     gloves
    0.56
    Act Density 0.003%

    No Known Activations