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

    Neuronpedia

    INDEX
    Explanations

    words related to initiating or causing responses or actions

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

    to cause an effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     religione
    -0.42
    __':
    -0.41
    LookAnd
    -0.40
    gjenge
    -0.39
     ElementRef
    -0.37
     direzione
    -0.37
    InputElement
    -0.37
     EClass
    -0.36
    EndGlobal
    -0.36
     None
    -0.36
    POSITIVE LOGITS
     menimbulkan
    0.65
     elicit
    0.64
     provoke
    0.63
     provoked
    0.61
     prompted
    0.59
     provoque
    0.59
     вызывает
    0.59
     provoquer
    0.59
     provoca
    0.58
     provoking
    0.57
    Act Density 0.056%

    No Known Activations