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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numeric values (numbers containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	core
    -0.07
     нуж
    -0.06
     revolver
    -0.06
    圭圭
    -0.06
     vestib
    -0.06
    population
    -0.06
    Iso
    -0.06
     unterschied
    -0.06
     hunger
    -0.06
     مف
    -0.06
    POSITIVE LOGITS
    STS
    0.07
     معدن
    0.06
     октября
    0.06
    (optimizer
    0.06
     spinner
    0.06
    <O
    0.06
    '](
    0.06
    (CharSequence
    0.06
    자인
    0.06
     jméno
    0.06
    Act Density 0.032%

    No Known Activations