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

    Neuronpedia

    INDEX
    Explanations

    few options, JSON objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    शय
    0.53
    ilibr
    0.52
    amide
    0.48
     (
    0.47
     ABSORBED
    0.47
     წინ
    0.47
     }{}_{\
    0.47
     domani
    0.47
    pInBuffer
    0.46
    感知
    0.44
    POSITIVE LOGITS
    ло
    0.51
    Atlanta
    0.48
    咒
    0.48
    드
    0.47
    Blo
    0.47
     Fle
    0.46
    Fle
    0.46
     Fracture
    0.46
    BROOK
    0.45
    क्यू
    0.45
    Act Density 0.000%

    No Known Activations