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

    Neuronpedia

    INDEX
    Explanations

    Score, causing, pause, deeply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ampl
    0.41
    OrElse
    0.40
    يتها
    0.40
     桌
    0.38
     سمجھتے
    0.38
    pasar
    0.36
     Ampl
    0.35
    렬
    0.35
     Dro
    0.35
     депози
    0.35
    POSITIVE LOGITS
    提供的
    0.41
     spät
    0.40
     estándares
    0.39
    ⊤
    0.38
     produktów
    0.38
     grij
    0.37
    큐
    0.37
    лых
    0.36
     Hemisphere
    0.36
    所
    0.36
    Act Density 0.071%

    No Known Activations