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

    Neuronpedia

    INDEX
    Explanations

    words and phrases expressing gratitude or appreciation

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

    prepositional phrases, foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arşivlendi
    -0.59
    __*/
    -0.55
     kasarigan
    -0.53
    лтемелер
    -0.53
    Ведь
    -0.49
     VIDEOTAPE
    -0.49
    MemoryWarning
    -0.49
    Cyfeiriadau
    -0.49
     Taktlose
    -0.49
    kwds
    -0.48
    POSITIVE LOGITS
     borboleta
    0.41
    RetentionPolicy
    0.41
     kunna
    0.40
    спу
    0.40
     pad
    0.40
     compresión
    0.39
    antMatchers
    0.38
    }{*}{
    0.37
     quibus
    0.36
     dormitórios
    0.36
    Act Density 0.142%

    No Known Activations