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

    Neuronpedia

    INDEX
    Explanations

    base and height

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ços
    0.95
    அல்ல
    0.94
     darn
    0.93
    скохозяй
    0.87
    twist
    0.85
    दीय
    0.84
    ches
    0.83
    <0x0C>
    0.81
    ahili
    0.81
    EXPER
    0.80
    POSITIVE LOGITS
    값
    1.15
    값을
    0.93
    স্থানীয়
    0.93
    값이
    0.91
    부분
    0.88
    haar
    0.85
    高
    0.84
    手指
    0.83
    less
    0.82
     shrouded
    0.81
    Act Density 0.441%

    No Known Activations