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

    Neuronpedia

    INDEX
    Explanations

    asterisk symbol

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point numeric literals (decimal numbers) found in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    乾
    -0.07
    Recording
    -0.06
     मई
    -0.06
     Garr
    -0.06
     embr
    -0.06
    .promise
    -0.06
    ,dim
    -0.06
     Nicol
    -0.06
    noun
    -0.06
    Impro
    -0.06
    POSITIVE LOGITS
    ải
    0.07
    jp
    0.07
    ลาด
    0.06
     almacen
    0.06
    >'+↵
    0.06
                 ↵
    0.06
    oglobin
    0.06
    PHP
    0.06
     zona
    0.06
    -dashboard
    0.06
    Act Density 0.004%

    No Known Activations