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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a shift into a particular state or condition

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

    fall into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Maximus
    -0.40
     Noma
    -0.39
     noDo
    -0.38
     أعلام
    -0.38
    पया
    -0.36
    ék
    -0.36
     VIAF
    -0.36
    elcome
    -0.36
     gì
    -0.35
    findpost
    -0.35
    POSITIVE LOGITS
     Falling
    0.61
    Falling
    0.59
    falling
    0.58
     falling
    0.58
     fell
    0.56
     FALL
    0.54
    Demografía
    0.51
     fallen
    0.49
     Fall
    0.49
    Fall
    0.48
    Act Density 0.011%

    No Known Activations