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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of lamp switch positions, i.e. the “on/off” switch and its on or off states.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    得到
    -0.07
     üzerinden
    -0.06
     correctly
    -0.06
    antal
    -0.06
     nog
    -0.06
     facet
    -0.06
     propriet
    -0.06
     COLOR
    -0.06
    vatel
    -0.06
    (address
    -0.06
    POSITIVE LOGITS
    ；
    0.07
    QRSTUV
    0.07
    чают
    0.06
    /stretch
    0.06
     okam
    0.06
     oci
    0.06
    Mozilla
    0.06
     výj
    0.06
     genomes
    0.06
     solitude
    0.06
    Act Density 0.187%

    No Known Activations