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

    Neuronpedia

    INDEX
    Explanations

    n

    np_max-act · gemini-2.0-flash

    The neuron activates on floating-point numeric literals (decimal fractions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    하지
    -0.07
    Helpers
    -0.06
     currently
    -0.06
     Faster
    -0.06
     ethical
    -0.06
    чі
    -0.06
    	answer
    -0.06
     oversh
    -0.06
     Here
    -0.06
     +#+#+#+#+#+
    -0.06
    POSITIVE LOGITS
     Celebrity
    0.07
    imension
    0.07
    oje
    0.07
    ريب
    0.07
    ुण
    0.06
     держ
    0.06
     Ung
    0.06
    .notifications
    0.06
     IDM
    0.06
    	menu
    0.06
    Act Density 0.048%

    No Known Activations