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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron activates on the phrase “the same way as,” i.e. when text matches that exact sequence.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Q
    -0.07
     recuper
    -0.06
    524
    -0.06
    	Q
    -0.06
     fully
    -0.06
     batteries
    -0.06
    006
    -0.06
     =================================================
    -0.06
     republice
    -0.06
     усі
    -0.06
    POSITIVE LOGITS
    .IP
    0.07
    .orig
    0.06
     IPs
    0.06
    assessment
    0.06
    ValidationError
    0.06
    /renderer
    0.06
    Unhandled
    0.06
     podob
    0.06
    .UI
    0.06
     nguồn
    0.06
    Act Density 0.001%

    No Known Activations