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

    Neuronpedia

    INDEX
    Explanations

    ensuring correctness or completeness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dovrebbe
    0.37
    }
    0.37
    '<
    0.36
    )
    0.35
    \
    0.35
    }=\
    0.33
     potrebbe
    0.33
     skulle
    0.33
    '
    0.32
     scler
    0.31
    POSITIVE LOGITS
    on
    0.46
    that
    0.42
    il
    0.40
    ok
    0.39
    고
    0.38
    ва
    0.38
     સારી
    0.37
    compliance
    0.37
    the
    0.37
    id
    0.37
    Act Density 0.086%

    No Known Activations