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

    Neuronpedia

    INDEX
    Explanations

    experiments

    np_max-act · gemini-2.0-flash

    the neuron is looking for numeric tokens (especially floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Alone
    -0.06
     の
    -0.06
    柱
    -0.06
     ноя
    -0.06
    ��
    -0.06
    -run
    -0.06
    praak
    -0.06
    sah
    -0.06
    .Click
    -0.06
    veys
    -0.06
    POSITIVE LOGITS
    {/*
    0.07
    ylan
    0.07
     semantics
    0.07
     imm
    0.06
     GOODMAN
    0.06
    guard
    0.06
    元素
    0.06
    Equipment
    0.06
    .cid
    0.06
     Cipher
    0.06
    Act Density 0.012%

    No Known Activations