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

    Neuronpedia

    INDEX
    Explanations

    or, other options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     అనేక
    0.47
    传承
    0.47
     magní
    0.47
     první
    0.47
     manière
    0.45
     अनेक
    0.45
     Tetrahedron
    0.45
     Fleurit
    0.45
     plena
    0.44
     purified
    0.43
    POSITIVE LOGITS
    又は
    0.44
    つまり
    0.44
     или
    0.40
     maupun
    0.38
    றிவு
    0.37
    或者是
    0.37
    ったり
    0.37
    หรือ
    0.36
    или
    0.35
     ataupun
    0.35
    Act Density 0.064%

    No Known Activations