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

    Neuronpedia

    INDEX
    Explanations

    far

    np_max-act · gemini-2.0-flash

    This neuron activates on the hedging phrase “as far as” (e.g. “As far as I can tell,” “As far as we can tell,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Using
    -0.07
    Trader
    -0.06
     RESPONS
    -0.06
    请输入
    -0.06
     Drone
    -0.06
     Clock
    -0.06
     rumored
    -0.06
    -0.06
    анням
    -0.06
     Schmidt
    -0.06
    POSITIVE LOGITS
    宙
    0.07
     مستق
    0.07
    	assertFalse
    0.06
    舞
    0.06
     Esta
    0.06
     περιο
    0.06
    στο
    0.06
    synthesize
    0.06
    encodeURIComponent
    0.06
    _wrap
    0.06
    Act Density 0.005%

    No Known Activations