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

    Neuronpedia

    INDEX
    Explanations

    running

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gön
    0.73
    ificação
    0.70
     remove
    0.69
    $">
    0.68
     Remove
    0.68
    ಟರ್
    0.67
    illator
    0.66
    ⣀
    0.66
     Dern
    0.66
    nikiem
    0.66
    POSITIVE LOGITS
     वॉ
    0.83
     खुश
    0.78
    POINTS
    0.74
    Points
    0.74
     ওয়া
    0.69
    etok
    0.69
     कहलाती
    0.67
     नाराज
    0.66
    SAP
    0.64
    Happy
    0.64
    Act Density 0.006%

    No Known Activations