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

    Neuronpedia

    INDEX
    Explanations

    list item starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    program
    0.45
     program
    0.45
     celebrated
    0.43
     sheds
    0.42
    办法
    0.39
    l
    0.39
     equilibria
    0.39
     shed
    0.39
    datum
    0.39
    shed
    0.38
    POSITIVE LOGITS
    𝓾
    0.49
     incluyendo
    0.49
    בר
    0.45
     vuole
    0.45
     Polaroid
    0.45
     imate
    0.44
     ہوتا
    0.44
    ப்பான
    0.44
     Gesù
    0.43
     veut
    0.43
    Act Density 0.001%

    No Known Activations