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

    Neuronpedia

    INDEX
    Explanations

    /apis

    np_max-act · gemini-2.0-flash

    The neuron fires on import path segments referring to the Kubernetes API “meta” package (e.g. “metav1”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     surface
    -0.08
    inou
    -0.06
     craft
    -0.06
     surfaces
    -0.06
     Resolution
    -0.06
     residue
    -0.06
     simulate
    -0.06
     refuse
    -0.06
    ró
    -0.06
    	height
    -0.06
    POSITIVE LOGITS
    /apis
    0.08
     ＼:
    0.07
    ONLY
    0.07
    uber
    0.07
    Ti
    0.07
    ／／
    0.07
    らない
    0.06
    �试
    0.06
     คณะ
    0.06
    !!
    0.06
    Act Density 0.000%

    No Known Activations