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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point numeric tokens (decimal fragments).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    難
    -0.07
    Api
    -0.06
     فرزند
    -0.06
    Helpers
    -0.06
    แข
    -0.06
     OK
    -0.06
    .pathname
    -0.06
    /connect
    -0.06
    okes
    -0.06
    /gtest
    -0.06
    POSITIVE LOGITS
     cur
    0.07
     music
    0.07
    });
↵
    0.06
     New
    0.06
    (pts
    0.06
    uely
    0.06
    irectional
    0.06
     glide
    0.06
     OF
    0.06
    має
    0.06
    Act Density 0.000%

    No Known Activations