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

    Neuronpedia

    INDEX
    Explanations

    Ralph and associated names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ply
    0.41
    ifiable
    0.39
    ttle
    0.39
     ove
    0.38
    の実
    0.38
    苖
    0.37
     আয়
    0.37
     systemat
    0.37
    劇
    0.36
    iths
    0.36
    POSITIVE LOGITS
    Ralph
    0.53
     Ralph
    0.52
     Waldo
    0.52
     ralph
    0.52
     lauren
    0.44
    ອ
    0.43
    ровали
    0.42
    товар
    0.39
    रोला
    0.38
    ﮐ
    0.38
    Act Density 0.000%

    No Known Activations