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

    Neuronpedia

    INDEX
    Explanations

    Code/File paths

    np_max-act · gemini-2.0-flash

    This neuron responds to floating‐point numbers—tokens representing decimal numeric values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    STAR
    -0.07
    Zero
    -0.07
     chồng
    -0.07
     speech
    -0.07
    ILLA
    -0.06
    니스
    -0.06
    empre
    -0.06
     клет
    -0.06
    ्छ
    -0.06
     Speech
    -0.06
    POSITIVE LOGITS
    Prosec
    0.06
    vari
    0.06
    	extern
    0.06
     gra
    0.06
    <Action
    0.06
    FORMANCE
    0.06
    �
    0.06
    	View
    0.06
     Цент
    0.06
    +='
    0.06
    Act Density 0.084%

    No Known Activations