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

    Neuronpedia

    INDEX
    Explanations

    %

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens—especially floating‐point numbers (often appearing in URL percent‐encodings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    亮
    -0.06
     blurred
    -0.06
    _H
    -0.06
     khiển
    -0.06
    13
    -0.06
     Blast
    -0.06
    بوب
    -0.06
     cou
    -0.06
     chơi
    -0.06
     Kaw
    -0.06
    POSITIVE LOGITS
     <%
    0.07
    .Region
    0.07
    ocene
    0.07
    ?s
    0.07
     stad
    0.06
     tighten
    0.06
    spirit
    0.06
    akte
    0.06
     myth
    0.06
    OTION
    0.06
    Act Density 0.007%

    No Known Activations