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

    Neuronpedia

    INDEX
    Explanations

    Spring Boot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    3.62
    (\
    3.48
    து
    3.46
    রে
    3.27
    ש
    3.18
     싶
    3.15
    র
    3.13
    ان
    3.03
    ম
    3.00
    ۲
    2.99
    POSITIVE LOGITS
    𝔂
    2.73
     dura
    2.71
    𝓪
    2.69
    ēc
    2.67
     pepp
    2.58
    шча
    2.57
    ड़ा
    2.54
    amaya
    2.52
    ч
    2.52
     cuentas
    2.51
    Act Density 0.022%

    No Known Activations