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

    Neuronpedia

    INDEX
    Explanations

    food and physics concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.47
    тие
    0.45
    წყვე
    0.44
    عود
    0.44
    ف
    0.43
     Tik
    0.43
     Necessity
    0.43
    سو
    0.42
     Hotels
    0.41
     Elekt
    0.40
    POSITIVE LOGITS
    ಡೆ
    0.49
     ruh
    0.49
     pressured
    0.47
     الذين
    0.47
     التي
    0.47
     bahsede
    0.47
     تر
    0.46
     كو
    0.46
     تاز
    0.45
     kojoj
    0.45
    Act Density 0.000%

    No Known Activations