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

    Neuronpedia

    INDEX
    Explanations

    pause function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ahirkan
    0.47
    pena
    0.47
     più
    0.47
     piatto
    0.46
     što
    0.46
     premio
    0.45
    brun
    0.45
     eren
    0.44
    禎
    0.44
     மாற்றம்
    0.43
    POSITIVE LOGITS
    0.48
    ad
    0.47
     expenses
    0.45
    इस
    0.43
     इस
    0.42
    cd
    0.41
    ir
    0.41
     Vegetation
    0.40
    kh
    0.40
     थो
    0.40
    Act Density 0.000%

    No Known Activations