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

    Neuronpedia

    INDEX
    Explanations

    titles and headings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Untuk
    0.50
    കൊ
    0.50
     karde
    0.47
    ład
    0.47
    Для
    0.47
     geändert
    0.47
    پ
    0.47
    اخ
    0.46
    Für
    0.46
    Provide
    0.45
    POSITIVE LOGITS
    semble
    0.57
     `>=`,
    0.50
    rice
    0.50
    trn
    0.47
    kule
    0.44
     CAE
    0.44
     fairness
    0.43
    seite
    0.43
    కూ
    0.43
    teen
    0.42
    Act Density 0.001%

    No Known Activations