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

    Neuronpedia

    INDEX
    Explanations

    handles database

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     florals
    0.49
     فريبي
    0.47
     unglaublich
    0.46
     zusätzlichen
    0.46
     flamboyant
    0.46
    অর্চনা
    0.45
     සඳහා
    0.45
     جديده
    0.43
    只限平日
    0.42
    অর্
    0.42
    POSITIVE LOGITS
    ole
    0.49
    .
    0.48
    aco
    0.48
    itudes
    0.47
    aturated
    0.46
     a
    0.46
    aba
    0.44
     .
    0.44
    ost
    0.43
    itta
    0.43
    Act Density 0.006%

    No Known Activations