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

    Neuronpedia

    INDEX
    Explanations

    depending on conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    baptism
    0.51
    |$
    0.44
    bigcap
    0.43
     notícias
    0.42
    AnimationFrame
    0.42
    bumper
    0.41
     milioane
    0.41
    इड
    0.40
    sda
    0.40
    луйста
    0.40
    POSITIVE LOGITS
     depending
    0.54
     Depending
    0.46
     Spec
    0.43
    depending
    0.43
     to
    0.43
    acio
    0.42
     dependent
    0.41
    可以通过
    0.41
    Depending
    0.41
    dependent
    0.40
    Act Density 0.001%

    No Known Activations