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

    Neuronpedia

    INDEX
    Explanations

    input validation and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     optimise
    0.46
     optimize
    0.46
    үү
    0.46
    otherapy
    0.45
     discover
    0.44
    اکہ
    0.43
     tı
    0.43
     hinzufügen
    0.43
     descoper
    0.43
     impacted
    0.42
    POSITIVE LOGITS
    ).
    0.50
    ্যা
    0.45
     bella
    0.45
    ردم
    0.45
    spending
    0.44
    }.
    0.43
     caracteres
    0.43
     Cip
    0.43
     florals
    0.43
    bloom
    0.42
    Act Density 0.000%

    No Known Activations