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

    Neuronpedia

    INDEX
    Explanations

    rewrites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    äus
    0.44
     waving
    0.41
    σουν
    0.40
    igable
    0.39
    নমেন্ট
    0.38
    winding
    0.38
    WIS
    0.38
    Watching
    0.38
    Ｗ
    0.38
    şim
    0.38
    POSITIVE LOGITS
    ite
    0.87
     rite
    0.81
     Rite
    0.80
    rites
    0.79
     Ritter
    0.79
    rite
    0.77
    Rite
    0.76
    ITE
    0.75
    ites
    0.74
     rit
    0.74
    Act Density 0.003%

    No Known Activations