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

    Neuronpedia

    INDEX
    Explanations

    descriptive qualities of objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lerinde
    0.64
    崱
    0.52
     Been
    0.50
    க்கப்பட்ட
    0.50
    nessy
    0.49
    泞
    0.46
     தினமும்
    0.45
    渴望
    0.44
    জীবী
    0.44
    lerini
    0.44
    POSITIVE LOGITS
    ج
    0.56
    3
    0.52
     micros
    0.52
     filler
    0.50
     discriminator
    0.48
    ם
    0.48
     boat
    0.48
    ق
    0.47
    2
    0.47
    4
    0.46
    Act Density 0.255%

    No Known Activations