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

    Neuronpedia

    INDEX
    Explanations

    crystall

    np_max-act · gemini-2.0-flash

    This neuron activates on words related to crystals or crystallization.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    agas
    -0.07
     kos
    -0.07
     Paleo
    -0.07
     Sao
    -0.07
     saf
    -0.07
     Shak
    -0.07
     gf
    -0.07
     pork
    -0.06
    _RANGE
    -0.06
     breat
    -0.06
    POSITIVE LOGITS
     crystall
    0.10
     chrono
    0.07
    .can
    0.07
    었다
    0.07
     🙂
    0.07
     closeModal
    0.06
    _InitStruct
    0.06
    ุษย
    0.06
    .Then
    0.06
     Nebraska
    0.06
    Act Density 0.002%

    No Known Activations