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

    Neuronpedia

    INDEX
    Explanations

    that is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     постро
    0.38
    ற்ற
    0.35
     години
    0.34
    z
    0.34
    aldb
    0.33
    beitet
    0.33
    एगी
    0.32
    }*/
    0.32
    ンジ
    0.31
    uí
    0.31
    POSITIVE LOGITS
    0.68
     are
    0.42
     is
    0.40
     at
    0.36
     in
    0.36
     watermelon
    0.35
     water
    0.35
     asbestos
    0.34
     $
    0.33
     out
    0.33
    Act Density 0.213%

    No Known Activations