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

    Neuronpedia

    INDEX
    Explanations

    Database/Table Extraction

    np_max-act · gemini-2.0-flash

    This neuron detects numeric tokens (both integers and decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ॉस
    -0.07
    �
    -0.07
    ولو
    -0.07
     подав
    -0.07
     에
    -0.06
    edium
    -0.06
     ques
    -0.06
    еним
    -0.06
    чай
    -0.06
    oň
    -0.06
    POSITIVE LOGITS
     Sinclair
    0.07
    VF
    0.06
    <<<<
    0.06
     Klein
    0.06
    (argv
    0.06
    (--
    0.06
    <Array
    0.06
     Claim
    0.06
     Trab
    0.06
    .ease
    0.06
    Act Density 0.012%

    No Known Activations