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

    Neuronpedia

    INDEX
    Explanations

    what to do if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KM
    0.45
    QC
    0.44
    IRY
    0.43
     Rajya
    0.42
     äuß
    0.42
     kommer
    0.41
    PE
    0.40
    abd
    0.40
    APR
    0.40
     பே
    0.39
    POSITIVE LOGITS
     wobec
    0.47
    ларга
    0.46
     действий
    0.43
    𝚒
    0.42
     કાર્યવાહી
    0.42
    ກັບ
    0.42
    Twig
    0.41
     terhadap
    0.41
     noviembre
    0.40
     તેને
    0.40
    Act Density 0.105%

    No Known Activations