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

    Neuronpedia

    INDEX
    Explanations

    foreign language or domain specific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Prothorax
    0.55
    MODEL
    0.51
     Constable
    0.50
    CEPTION
    0.48
    基金产品
    0.48
    ModelComponent
    0.48
    Delegate
    0.47
     Prothorax
    0.47
    PRINT
    0.47
    挲
    0.47
    POSITIVE LOGITS
     é
    0.50
    л
    0.50
     chines
    0.49
     équipes
    0.49
    w
    0.49
     события
    0.47
     esports
    0.47
     tài
    0.46
     onyx
    0.46
     event
    0.46
    Act Density 0.000%

    No Known Activations