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

    Neuronpedia

    INDEX
    Explanations

    forms, feel, becomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estándares
    0.46
    rl
    0.43
    eln
    0.43
    raded
    0.43
     AMT
    0.43
    txt
    0.43
    pia
    0.43
    total
    0.42
    -
    0.42
    يك
    0.42
    POSITIVE LOGITS
     mainWindow
    0.51
     פע
    0.49
     suasana
    0.49
     נו
    0.48
     زع
    0.47
     כ
    0.46
     論
    0.45
    Developer
    0.45
     дуже
    0.44
    PhysicalDevice
    0.44
    Act Density 0.001%

    No Known Activations