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

    Neuronpedia

    INDEX
    Explanations

    common words/fragments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     monog
    0.57
    presentasikan
    0.50
     prid
    0.49
     scuole
    0.49
     관
    0.49
     notion
    0.49
     මත
    0.49
     coalescence
    0.48
     wichtige
    0.47
     solemn
    0.46
    POSITIVE LOGITS
    ICAGO
    0.88
    vironment
    0.80
    icago
    0.78
    ञ
    0.77
    ristmas
    0.75
    aintiff
    0.73
    incipal
    0.72
    blic
    0.69
    swers
    0.69
    ategy
    0.68
    Act Density 0.022%

    No Known Activations