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

    Neuronpedia

    INDEX
    Explanations

    draw

    np_max-act · gemini-2.0-flash

    This neuron activates on terms referring to material stretching or drawing processes (e.g. drawn, drawing, attenuated).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    dict
    -0.07
    *</
    -0.06
     RNA
    -0.06
     Otto
    -0.06
     Plant
    -0.06
     रव
    -0.06
    る
    -0.06
    EQUAL
    -0.06
    eping
    -0.06
    WEST
    -0.06
    POSITIVE LOGITS
    polation
    0.07
     waving
    0.06
     agricult
    0.06
     disciplines
    0.06
     entwick
    0.06
     welcomes
    0.06
     sacrific
    0.06
     nomin
    0.06
     assignments
    0.06
    Reduce
    0.06
    Act Density 0.006%

    No Known Activations