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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    The neuron is picking out floating‐point numerical values (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    teş
    -0.07
     nộp
    -0.07
    /debug
    -0.07
     newPassword
    -0.07
     Valk
    -0.06
     Geç
    -0.06
    ^[
    -0.06
    _SENT
    -0.06
    คณะ
    -0.06
    .VAL
    -0.06
    POSITIVE LOGITS
    avo
    0.07
    ليزية
    0.06
     ownership
    0.06
     Town
    0.06
     Virginia
    0.06
     star
    0.06
    542
    0.06
    бор
    0.06
     apparent
    0.06
     O
    0.06
    Act Density 0.024%

    No Known Activations