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

    Neuronpedia

    INDEX
    Explanations

    ensuring compliance or accuracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    1.34
    )
    1.23
    }
    1.05
    );*/
    1.02
    '*
    1.01
    ),
    1.00
    '<
    1.00
     tarafından
    1.00
    ۳
    0.99
    <0x0D>
    0.96
    POSITIVE LOGITS
    on
    1.96
    고
    1.49
    ro
    1.38
    ین
    1.33
    ensure
    1.33
    ח
    1.29
    р
    1.26
    il
    1.23
    u
    1.23
    ↵
    1.21
    Act Density 0.079%

    No Known Activations