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

    Neuronpedia

    INDEX
    Explanations

    Paul Walker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ühe
    0.48
    梶
    0.47
     sever
    0.46
    ゆ
    0.45
     colorless
    0.45
    ид
    0.45
    תר
    0.45
    勋
    0.44
     kendi
    0.42
     dolu
    0.42
    POSITIVE LOGITS
    ut
    0.59
     Animations
    0.50
    rant
    0.49
    elines
    0.49
    ulations
    0.48
    rå
    0.48
    ration
    0.48
    als
    0.48
     ім
    0.47
     Occasionally
    0.47
    Act Density 0.000%

    No Known Activations