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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (numbers with decimal points).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     feels
    -0.07
    カテ
    -0.07
    优秀
    -0.07
     treason
    -0.06
    л
    -0.06
     Τε
    -0.06
    έ
    -0.06
    �
    -0.06
     kisses
    -0.06
    Years
    -0.06
    POSITIVE LOGITS
     exchanging
    0.07
     guarda
    0.07
    filename
    0.07
    WEB
    0.06
    blob
    0.06
     Text
    0.06
    'order
    0.06
     Automated
    0.06
     mutex
    0.06
     supplemental
    0.06
    Act Density 0.031%

    No Known Activations