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

    Neuronpedia

    INDEX
    Explanations

    quickly passed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hindu
    0.41
     ನ್ಯ
    0.39
    dressing
    0.38
     membran
    0.38
    PACK
    0.37
    Updating
    0.37
    väl
    0.37
     diameters
    0.37
     multib
    0.37
    chap
    0.36
    POSITIVE LOGITS
    nnnn
    0.39
     nCurrent
    0.37
     TouchUtils
    0.37
    achio
    0.37
    MN
    0.36
    FlowNode
    0.36
     घ
    0.35
    matig
    0.35
    筍
    0.35
    芘
    0.35
    Act Density 0.001%

    No Known Activations