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

    Neuronpedia

    INDEX
    Explanations

    echo

    np_max-act · gemini-2.0-flash

    This neuron activates on floating‐point numeric literals (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     getP
    -0.09
    	lp
    -0.06
     seals
    -0.06
     IC
    -0.06
    Tween
    -0.06
    _password
    -0.06
    едаг
    -0.06
     legs
    -0.06
    Layout
    -0.06
    	password
    -0.06
    POSITIVE LOGITS
     bubb
    0.07
     loophole
    0.06
    .Dropout
    0.06
    .Trace
    0.06
    处
    0.06
     пу
    0.06
    汉
    0.06
     phận
    0.06
    ，”
    0.06
    pread
    0.06
    Act Density 0.014%

    No Known Activations