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

    Neuronpedia

    INDEX
    Explanations

    how to solve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ámbito
    0.40
    segaretro
    0.39
     franqu
    0.38
     tartan
    0.38
     sfai
    0.38
     reuniones
    0.38
     biodegrad
    0.38
     bancos
    0.38
    Bechyné
    0.37
    .-\
    0.35
    POSITIVE LOGITS
     Answer
    0.54
    Answer
    0.52
     Solution
    0.49
    Solution
    0.47
    Video
    0.47
     Solutions
    0.46
     Video
    0.46
    ↵
    0.46
     Question
    0.45
    Question
    0.44
    Act Density 0.000%

    No Known Activations