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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash

    This neuron responds to decimal numeric tokens, i.e. floating-point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -toggler
    -0.07
     улыб
    -0.06
    .Transform
    -0.06
     favicon
    -0.06
     updater
    -0.06
    束
    -0.06
    interval
    -0.06
     حزب
    -0.06
     ایست
    -0.06
    	Error
    -0.05
    POSITIVE LOGITS
     násled
    0.07
    궁
    0.07
    ]}
    0.07
    .boot
    0.07
    ))
    0.06
    dıktan
    0.06
     ska
    0.06
    [$
    0.06
    　l
    0.06
     binds
    0.06
    Act Density 0.510%

    No Known Activations