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

    Neuronpedia

    INDEX
    Explanations

    syntax related to decision-making and input handling in programming

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

    Code or math containing an equals sign

    np_acts-logits-general · gemini-2.0-flash

    asking for input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )}_
    -0.54
    libur
    -0.51
     Kull
    -0.51
     ivelany
    -0.50
    ância
    -0.49
     AQUÍ
    -0.49
    inerja
    -0.48
     oprot
    -0.47
     Delivery
    -0.47
     censiti
    -0.47
    POSITIVE LOGITS
     input
    1.40
    input
    1.26
    Input
    1.09
     Input
    1.08
     prompt
    1.07
     inputs
    1.03
    prompt
    1.02
    Prompt
    0.99
    输入
    0.98
     ask
    0.98
    Act Density 0.168%

    No Known Activations