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

    Neuronpedia

    INDEX
    Explanations

    Hollywood hopefuls or judgments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ото
    0.46
    д
    0.46
    హ్
    0.46
    дцать
    0.46
    ר
    0.46
    ﻬ
    0.46
    随意
    0.45
    ारा
    0.45
    א
    0.45
    ഹ്
    0.45
    POSITIVE LOGITS
    és
    0.47
    system
    0.47
    rett
    0.47
     syringes
    0.46
    shelf
    0.46
     backtracking
    0.46
     pushes
    0.45
     calcium
    0.45
     Restoration
    0.45
     slapping
    0.45
    Act Density 0.001%

    No Known Activations