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

    Neuronpedia

    INDEX
    Explanations

    fall

    np_max-act · gemini-2.0-flash

    This neuron responds to floating-point numeric tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Müz
    -0.07
     isc
    -0.07
    wire
    -0.07
    program
    -0.07
    ComputedStyle
    -0.07
     größ
    -0.07
    DebugEnabled
    -0.06
     vigorously
    -0.06
    	use
    -0.06
     เคร
    -0.06
    POSITIVE LOGITS
     fall
    0.14
     Fall
    0.14
     falls
    0.13
    fall
    0.12
     falling
    0.12
     fell
    0.11
     Falls
    0.11
     fallen
    0.11
    Fall
    0.11
     FALL
    0.10
    Act Density 0.021%

    No Known Activations