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

    Neuronpedia

    INDEX
    Explanations

    intricate details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ához
    0.55
     rije
    0.53
    )^{*}\
    0.50
    txtarea
    0.50
    źdz
    0.49
    rarea
    0.48
    ^{*}}\
    0.48
    athar
    0.48
    쐞
    0.47
    að
    0.47
    POSITIVE LOGITS
     on
    0.69
     of
    0.59
    ב
    0.55
     at
    0.53
     making
    0.52
     cruises
    0.52
    ,”
    0.51
     alleging
    0.51
     int
    0.50
    ,"
    0.50
    Act Density 0.002%

    No Known Activations