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

    Neuronpedia

    INDEX
    Explanations

    . " "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     madres
    -0.86
    uoco
    -0.85
    ğren
    -0.84
     jú
    -0.83
     kabát
    -0.82
    durante
    -0.82
     revolucion
    -0.81
    ENIX
    -0.81
    eload
    -0.80
     Antrags
    -0.79
    POSITIVE LOGITS
     these
    1.12
     once
    0.97
     vervolgens
    0.92
    これらの
    0.88
     aforementioned
    0.85
     Fg
    0.85
    Once
    0.82
    postIndex
    0.82
    这些
    0.81
    once
    0.79
    Act Density 0.102%

    No Known Activations