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 divisibility‐check expressions using the modulo operator (e.g. “i % 3 == 0” or “i % 5 == 0”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ucu
    -0.06
    Curso
    -0.06
    erto
    -0.06
    _FW
    -0.06
     �
    -0.06
    逐
    -0.06
    EdgeInsets
    -0.06
    .SharedPreferences
    -0.06
    _latitude
    -0.06
    POSITIVE LOGITS
    apl
    0.06
     unpublished
    0.06
     amended
    0.06
     없는
    0.06
     Hidden
    0.06
     opinion
    0.06
     تلاش
    0.06
    REP
    0.06
     correct
    0.06
    .setObjectName
    0.06
    Act Density 0.003%

    No Known Activations