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

    Neuronpedia

    INDEX
    Explanations

    landing jobs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ધા
    0.38
     Eqs
    0.38
    >{{
    0.38
    amides
    0.37
    至于
    0.37
    attice
    0.37
     हानि
    0.36
    ப்புகள்
    0.36
    tank
    0.36
     stifle
    0.35
    POSITIVE LOGITS
     fratello
    0.45
     Dow
    0.43
     अनो
    0.42
     ю
    0.40
    ्यालय
    0.39
     Wain
    0.39
    눅
    0.39
     ৮
    0.38
     ۶
    0.38
     ۸
    0.38
    Act Density 0.000%

    No Known Activations