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

    Neuronpedia

    INDEX
    Explanations

    documentation and code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ])]
    -1.09
    ]$.
    -1.05
    }()
    -1.01
    ModelAdmin
    -1.00
     princesa
    -0.95
    ,:)
    -0.94
    ,:),
    -0.94
     */
    -0.93
     \%)$
    -0.93
     pistas
    -0.92
    POSITIVE LOGITS
     nebst
    1.00
    也都
    0.99
     aufgeführt
    0.95
     vw
    0.86
    ępo
    0.86
     gelegt
    0.86
     eingerichtet
    0.85
     bezüglich
    0.85
    就没有
    0.84
     dawg
    0.82
    Act Density 0.060%

    No Known Activations