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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </u>
    0.67
    .**
    0.66
    హు
    0.65
    WARNING
    0.65
    Chord
    0.64
    Magenta
    0.63
    .
    0.63
    .)
    0.63
    )
    0.62
    )**
    0.60
    POSITIVE LOGITS
    ệc
    0.90
     administrative
    0.84
     morale
    0.84
     tasks
    0.84
    […]
    0.83
     judicial
    0.83
     阅读全文
    0.83
     необходимость
    0.80
     demais
    0.79
     dispos
    0.79
    Act Density 0.038%

    No Known Activations