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

    Neuronpedia

    INDEX
    Explanations

    lists and important information about adverse reactions and elements within documents

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

    proofs of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -0.36
     nejs
    -0.32
     parecía
    -0.31
     guste
    -0.31
    providedIn
    -0.31
    baguna
    -0.29
     parezca
    -0.29
     olun
    -0.28
     onCreateView
    -0.26
     pareció
    -0.26
    POSITIVE LOGITS
    Atsauces
    0.64
    طلحات
    0.63
    ismet
    0.59
     Walkover
    0.59
     defaultstate
    0.57
    BufferException
    0.57
    Viited
    0.55
    WriteAttribute
    0.55
    SequentialGroup
    0.55
     الرياضيه
    0.54
    Act Density 0.003%

    No Known Activations