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

    Neuronpedia

    INDEX
    Explanations

    Questions and answers

    np_max-act · gemini-2.0-flash

    This neuron activates specifically on occurrences of the word “mountain” (and its close morphological variants).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _RM
    -0.07
    StepThrough
    -0.07
     Stan
    -0.06
     投稿
    -0.06
    .Results
    -0.06
     reject
    -0.06
    	use
    -0.06
    (fmt
    -0.06
     kidd
    -0.06
     Hour
    -0.06
    POSITIVE LOGITS
    ulum
    0.07
    łą
    0.07
     olig
    0.07
    oneksi
    0.07
    olkata
    0.07
     sr
    0.07
    حاد
    0.07
     inclination
    0.06
    ائرة
    0.06
    ')));↵↵
    0.06
    Act Density 0.186%

    No Known Activations