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

    Neuronpedia

    INDEX
    Explanations

    categories, types, and types of impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ভৌম
    0.41
    CLOCK
    0.39
     Connie
    0.39
    ൂപ
    0.39
     Madeleine
    0.39
    袮
    0.38
    claves
    0.38
     공연
    0.38
     ನಾನು
    0.38
    Ꮀ
    0.37
    POSITIVE LOGITS
     เง
    0.42
     simplistic
    0.40
     girth
    0.40
    Loaded
    0.38
     loaded
    0.38
     Load
    0.38
     लोड
    0.38
     load
    0.37
    しなければ
    0.36
    gten
    0.36
    Act Density 0.001%

    No Known Activations