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

    Neuronpedia

    INDEX
    Explanations

    HTML form action attributes

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

    action attribute or parameter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.70
    ſelf
    -0.66
     الرياضيه
    -0.65
    AsUp
    -0.63
     pleaſure
    -0.60
    الإنجليزية
    -0.57
     fufficient
    -0.56
    Personendaten
    -0.55
    thâu
    -0.55
     Majefty
    -0.54
    POSITIVE LOGITS
     action
    0.99
    action
    0.80
     ACTION
    0.76
     Action
    0.75
    Action
    0.69
     acción
    0.66
     actie
    0.64
    ACTION
    0.59
     ação
    0.59
     actions
    0.57
    Act Density 0.000%

    No Known Activations