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

    Neuronpedia

    INDEX
    Explanations

    abstract legal concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    类型
    0.71
    6
    0.68
    आज
    0.68
    jeto
    0.67
    5
    0.67
    decorators
    0.66
    9
    0.66
    On
    0.63
    擔任
    0.63
     aient
    0.63
    POSITIVE LOGITS
     altas
    0.84
     cerebral
    0.77
     UCL
    0.77
    DeviceCompliance
    0.75
    ಯ್
    0.75
     nokta
    0.75
     an
    0.74
    ﻢ
    0.74
    лары
    0.73
     każdego
    0.73
    Act Density 0.000%

    No Known Activations