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

    Neuronpedia

    INDEX
    Explanations

    input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یک
    0.51
    ک
    0.49
    াক
    0.47
    зумі
    0.46
    Università
    0.45
    عب
    0.44
    ил
    0.44
    бли
    0.44
    لک
    0.44
    ار
    0.44
    POSITIVE LOGITS
    ting
    0.68
    ted
    0.54
     Input
    0.50
     input
    0.48
     stream
    0.46
    ten
    0.45
     newInput
    0.43
     sanit
    0.42
     getInput
    0.41
    1
    0.41
    Act Density 0.055%

    No Known Activations