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

    Neuronpedia

    INDEX
    Explanations

    20th Century

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }$}
    0.59
    }}}{
    0.58
    }$.
    0.54
    }$\
    0.54
    های
    0.54
     deflect
    0.54
    }\\
    0.52
    ⺆
    0.52
    と思います
    0.51
    ))\
    0.51
    POSITIVE LOGITS
     silam
    0.70
    '
    0.69
    에
    0.67
    に
    0.65
    ity
    0.58
    ities
    0.58
    महिला
    0.58
    ron
    0.57
    ite
    0.56
    шому
    0.54
    Act Density 1.068%

    No Known Activations