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

    Neuronpedia

    INDEX
    Explanations

    8-bit and 3D modeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BECAUSE
    0.38
     最后
    0.37
     یعنی
    0.35
     Creating
    0.35
     Dataset
    0.35
     因為
    0.34
     由于
    0.34
    (//
    0.34
    Посилання
    0.33
     আস্থা
    0.33
    POSITIVE LOGITS
     volt
    0.46
     fifth
    0.46
     eighteenth
    0.43
     artistic
    0.43
     nineteenth
    0.40
     tiered
    0.39
     sixth
    0.39
     dimensional
    0.38
     eighth
    0.38
     centimet
    0.38
    Act Density 0.010%

    No Known Activations