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

    Neuronpedia

    INDEX
    Explanations

    listing numbers after phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    АН
    0.41
    ्यूड
    0.35
    рованием
    0.35
     baseman
    0.34
    слан
    0.34
    าส
    0.33
    𝖑
    0.33
     grievance
    0.33
    літ
    0.33
    ванием
    0.33
    POSITIVE LOGITS
     તથા
    0.45
     etc
    0.42
     등이
    0.40
    甚至是
    0.38
     etcétera
    0.38
     futhi
    0.38
     등으로
    0.37
     그다음에
    0.37
     वगैरह
    0.36
     इत्यादी
    0.36
    Act Density 0.182%

    No Known Activations