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

    Neuronpedia

    INDEX
    Explanations

    ZFS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ragnar
    0.78
     always
    0.72
    CCESS
    0.69
     hockey
    0.67
     hit
    0.64
     sempre
    0.64
    始终
    0.63
     toujours
    0.63
     order
    0.63
     cr
    0.62
    POSITIVE LOGITS
     zz
    1.09
     ZnO
    0.92
    Zx
    0.89
     ZIP
    0.89
     Zor
    0.88
     ZZ
    0.88
    zt
    0.85
     PZ
    0.85
    ZI
    0.84
    PosZ
    0.83
    Act Density 0.202%

    No Known Activations