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

    Neuronpedia

    INDEX
    Explanations

    Google DeepMind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rafpunkte
    0.65
    kopp
    0.65
     রানের
    0.65
    medallas
    0.64
    instruction
    0.63
     xanth
    0.63
     montaña
    0.61
    จทย์
    0.61
    isal
    0.60
    teren
    0.60
    POSITIVE LOGITS
    HAR
    0.55
    V
    0.54
     HAR
    0.52
     V
    0.52
    नल
    0.50
    HS
    0.50
    ハ
    0.50
    滏
    0.49
    har
    0.49
     Hiz
    0.49
    Act Density 0.316%

    No Known Activations