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

    Neuronpedia

    INDEX
    Explanations

    origin and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     යුතු
    0.42
    ћа
    0.38
    ไต
    0.36
    xf
    0.36
     স্বাগত
    0.35
     प्रीवियस
    0.35
    までに
    0.35
    renaline
    0.34
    :=
    0.34
    Approach
    0.34
    POSITIVE LOGITS
     originated
    2.69
     originate
    2.30
     originates
    2.27
     origins
    2.14
     origin
    2.05
     origen
    2.05
    origin
    2.03
     originating
    1.99
     origine
    1.99
     origem
    1.99
    Act Density 0.039%

    No Known Activations