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

    Neuronpedia

    INDEX
    Explanations

    historical events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    L
    0.51
    Rare
    0.50
    r
    0.49
    v
    0.49
     Been
    0.47
     been
    0.45
    Y
    0.43
    H
    0.43
    rare
    0.42
    mer
    0.42
    POSITIVE LOGITS
     μα
    0.56
     মিনিটে
    0.55
    დომ
    0.55
    렇게
    0.51
    ﺏ
    0.51
    𒍪
    0.49
     방정
    0.48
    ſed
    0.48
     fatigued
    0.48
    य़ा
    0.48
    Act Density 0.002%

    No Known Activations