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

    Neuronpedia

    INDEX
    Explanations

    core idea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    probably
    0.76
     probably
    0.68
    FAIL
    0.67
    јо
    0.67
    Probably
    0.66
     provavelmente
    0.65
     probabilmente
    0.64
    AMPLES
    0.63
    IAM
    0.63
     probablemente
    0.63
    POSITIVE LOGITS
     idea
    4.77
     notion
    3.95
    idea
    3.95
     concept
    3.78
     ideia
    3.64
     Idea
    3.62
    idée
    3.46
    Idea
    3.39
     idée
    3.22
     идея
    3.13
    Act Density 0.444%

    No Known Activations