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

    Neuronpedia

    INDEX
    Explanations

    True

    np_max-act · gemini-2.0-flash

    This neuron remains inactive and does not detect any particular tokens or patterns.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     thích
    -0.06
    .serial
    -0.06
     tests
    -0.06
    _PARAMS
    -0.06
    sın
    -0.06
     Part
    -0.06
    	a
    -0.06
    licity
    -0.06
     murder
    -0.05
    _NR
    -0.05
    POSITIVE LOGITS
    nish
    0.07
     cong
    0.07
     marrow
    0.07
     bakım
    0.07
     glanced
    0.06
    newInstance
    0.06
    .structure
    0.06
    езд
    0.06
     Vers
    0.06
     Educ
    0.06
    Act Density 0.003%

    No Known Activations