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

    Neuronpedia

    INDEX
    Explanations

    scheduling and method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     अनुशासन
    0.67
    靄
    0.66
    ಷ್ಠ
    0.65
    𒁍
    0.65
     basaltes
    0.64
     Kardashians
    0.59
    aisia
    0.58
    akun
    0.58
    ᆢ
    0.58
    ಸ್ಥ
    0.56
    POSITIVE LOGITS
    T
    0.79
    A
    0.79
     die
    0.76
     de
    0.75
    k
    0.74
     je
    0.74
    I
    0.70
    F
    0.68
     que
    0.67
     ni
    0.67
    Act Density 0.000%

    No Known Activations