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

    Neuronpedia

    INDEX
    Explanations

    Hebrew names of God

    np_max-act · gemini-2.0-flash

    This neuron activates on the placeholder “NAME_1” (and its variants with numeric suffixes), i.e. tokens referring to that specific named Gospel reference.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Rox
    -0.08
    oze
    -0.06
     Webster
    -0.06
    .gradient
    -0.06
    uco
    -0.06
     сель
    -0.06
     ViewChild
    -0.06
    -outline
    -0.06
    descr
    -0.06
     winding
    -0.06
    POSITIVE LOGITS
     sufferers
    0.07
    0.07
    隆
    0.06
    IK
    0.06
     şar
    0.06
     Rights
    0.06
     Camel
    0.06
    acao
    0.06
    Rights
    0.06
     relying
    0.06
    Act Density 0.010%

    No Known Activations