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

    Neuronpedia

    INDEX
    Explanations

    by contracting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     डियर
    0.47
     Kisan
    0.41
    पीरियंस
    0.40
     riego
    0.40
    𒋛
    0.40
     ditches
    0.39
     faço
    0.39
     पार्क
    0.39
    APDS
    0.39
    ียม
    0.38
    POSITIVE LOGITS
    filename
    0.38
    త్
    0.38
    Integral
    0.38
     Overview
    0.37
    Recall
    0.37
    ymbol
    0.36
     integral
    0.36
    тка
    0.35
     w
    0.35
    Symbol
    0.35
    Act Density 0.000%

    No Known Activations