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

    Neuronpedia

    INDEX
    Explanations

    y coordinate assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unarmed
    0.43
    LVector
    0.43
    uniary
    0.39
     বিনাম
    0.39
    ~!
    0.39
     படை
    0.38
    ushchev
    0.38
    िस्तान
    0.38
     intermediary
    0.37
    POSITORY
    0.37
    POSITIVE LOGITS
    ree
    0.43
     Altitude
    0.42
    altitude
    0.41
     altitude
    0.40
     Höhen
    0.40
     altura
    0.40
     njegove
    0.40
     njeg
    0.39
     sơ
    0.39
     njegova
    0.39
    Act Density 0.048%

    No Known Activations