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

    Neuronpedia

    INDEX
    Explanations

    code and real estate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spelling
    1.00
    åk
    0.96
     cotisation
    0.95
    +_
    0.94
     secures
    0.93
    +(-
    0.92
    spell
    0.91
    ש
    0.89
    暨
    0.89
     და
    0.88
    POSITIVE LOGITS
     perf
    0.92
     Là
    0.91
    ように
    0.89
    ható
    0.89
     besondere
    0.89
    सला
    0.86
     vistas
    0.85
    娜
    0.84
     gratuit
    0.84
     музе
    0.84
    Act Density 0.008%

    No Known Activations