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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to occurrences of the verb “do.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Needless
    -0.07
    	left
    -0.07
    Establish
    -0.06
    需要
    -0.06
     meg
    -0.06
     अर
    -0.06
    _Internal
    -0.06
     nurs
    -0.06
     *)&
    -0.06
    _Vert
    -0.06
    POSITIVE LOGITS
     LOSS
    0.07
     deline
    0.07
     Fischer
    0.06
     Servlet
    0.06
    orque
    0.06
     alleles
    0.06
    opt
    0.06
     hành
    0.06
    oloj
    0.06
    .sqlite
    0.06
    Act Density 0.002%

    No Known Activations