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

    Neuronpedia

    INDEX
    Explanations

    Fortify Program

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cinta
    0.31
     собы
    0.31
     specifiche
    0.31
    .
    0.30
     necessidades
    0.29
     Derechos
    0.28
     ۵
    0.27
     नये
    0.27
    Elementos
    0.27
     batu
    0.27
    POSITIVE LOGITS
     with
    0.33
     for
    0.31
    t
    0.31
    。
    0.30
    dır
    0.30
     from
    0.28
     be
    0.27
     amendment
    0.27
    ished
    0.27
    BERG
    0.26
    Act Density 0.082%

    No Known Activations