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

    Neuronpedia

    INDEX
    Explanations

    mutual aid networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डायरे
    0.82
     демокра
    0.80
     Positioning
    0.78
    മുണ്ട്
    0.74
     ката
    0.70
    בּ
    0.69
     Он
    0.68
    Browser
    0.68
     기준
    0.66
    Catalogue
    0.66
    POSITIVE LOGITS
    ेष
    0.75
    ừ
    0.75
    datum
    0.66
     Saturday
    0.66
     Jena
    0.66
     adherent
    0.66
     save
    0.65
    elementary
    0.63
     ca
    0.63
    早期
    0.63
    Act Density 0.000%

    No Known Activations