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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any text—it remains inactive (all-zero activations).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Skinny
    -0.07
    elts
    -0.07
    osos
    -0.06
    ũ
    -0.06
     DESIGN
    -0.06
    >C
    -0.06
    .mount
    -0.06
    ert
    -0.06
     MOCK
    -0.06
     desert
    -0.06
    POSITIVE LOGITS
    ikh
    0.07
    (Database
    0.07
    affiliate
    0.06
    .Graphics
    0.06
     advantageous
    0.06
    izm
    0.06
     sister
    0.06
    =['
    0.06
    	select
    0.06
    iking
    0.06
    Act Density 0.002%

    No Known Activations