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

    Neuronpedia

    INDEX
    Explanations

    file manager and Android

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    άζ
    0.39
     pik
    0.39
     يأ
    0.38
    䀎
    0.38
     hous
    0.38
     Meek
    0.37
     loop
    0.37
    BUGFS
    0.36
     Imag
    0.36
     Loop
    0.35
    POSITIVE LOGITS
     महात्मा
    0.44
     sveta
    0.38
    da
    0.38
    ไหน
    0.37
    fest
    0.36
    Victoria
    0.36
     đẳng
    0.36
     Hutchinson
    0.35
     रोप
    0.35
    Sun
    0.35
    Act Density 0.001%

    No Known Activations