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

    Neuronpedia

    INDEX
    Explanations

    input

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “input.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    33
    -0.08
    22
    -0.07
    193
    -0.07
     Chronic
    -0.07
    achie
    -0.07
     marathon
    -0.07
    43
    -0.07
     bear
    -0.07
    واره
    -0.06
     за
    -0.06
    POSITIVE LOGITS
     Input
    0.11
     input
    0.10
    input
    0.10
    Input
    0.10
    InputDialog
    0.09
    μπ
    0.09
    up
    0.09
    InputGroup
    0.09
    inputs
    0.08
    .input
    0.08
    Act Density 0.046%

    No Known Activations