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

    Neuronpedia

    INDEX
    Explanations

    in right

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.57
    ↵↵
    0.57
     have
    0.55
    problem
    0.55
    k
    0.54
    '
    0.54
    you
    0.53
     judge
    0.51
    N
    0.49
    He
    0.49
    POSITIVE LOGITS
     diesem
    0.84
     questa
    0.71
     accordance
    0.70
     dieser
    0.69
    vertebr
    0.68
     unserem
    0.68
     pursuant
    0.68
     этом
    0.67
     suốt
    0.67
     todays
    0.67
    Act Density 0.000%

    No Known Activations