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

    Neuronpedia

    INDEX
    Explanations

    this is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (-
    0.53
     Fittings
    0.51
    देखिए
    0.50
    Vé
    0.50
     లక్ష
    0.50
    ))-
    0.50
     Blvd
    0.48
     인해
    0.48
     dėl
    0.48
     Retrieve
    0.48
    POSITIVE LOGITS
    hello
    0.88
    another
    0.78
     otra
    0.77
     otro
    0.75
    foo
    0.74
     hello
    0.73
    Hello
    0.71
    我很
    0.71
    我可以
    0.70
     foo
    0.69
    Act Density 0.043%

    No Known Activations