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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash

    This neuron activates on floating-point numeric literals (tokens containing a decimal point and fractional part).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    стика
    -0.07
     參
    -0.07
    _queryset
    -0.07
    žit
    -0.07
     나를
    -0.07
     BITTE
    -0.06
    γ
    -0.06
     descripcion
    -0.06
     onu
    -0.06
     plaint
    -0.06
    POSITIVE LOGITS
     minimum
    0.06
    ()">↵
    0.06
    DMI
    0.06
     APPLY
    0.06
    %d
    0.06
     VW
    0.06
    :mm
    0.06
    uniform
    0.06
    .rmi
    0.06
    @m
    0.06
    Act Density 0.005%

    No Known Activations