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

    Neuronpedia

    INDEX
    Explanations

    help solve or choose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     позволя
    0.90
    льзя
    0.86
    Allow
    0.86
     Allowing
    0.85
     aiutare
    0.85
     thiab
    0.85
    allows
    0.81
    allow
    0.80
     afterDir
    0.79
    }}$-
    0.78
    POSITIVE LOGITS
     develop
    1.12
     navigate
    1.00
     out
    0.96
     develops
    0.94
     succeed
    0.94
     developing
    0.91
    解決
    0.88
    navigate
    0.86
     achieve
    0.86
     hazırlan
    0.85
    Act Density 0.512%

    No Known Activations