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

    Neuronpedia

    INDEX
    Explanations

    using specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tast
    2.16
     alla
    2.13
    бі
    2.02
    𝙱
    2.01
     fatta
    1.96
     दरअसल
    1.93
     slik
    1.92
    вання
    1.85
    тина
    1.85
    ارڈ
    1.83
    POSITIVE LOGITS
    atamente
    2.16
    notin
    2.02
    ς
    2.00
    فري
    2.00
     तौर
    1.98
     ureth
    1.97
     eloquently
    1.96
    textField
    1.94
    ially
    1.92
    মতো
    1.92
    Act Density 0.453%

    No Known Activations