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

    Neuronpedia

    INDEX
    Explanations

    the most or the core

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的影响
    0.31
     algumas
    0.29
    -
    0.29
    nThe
    0.29
     zowel
    0.28
    The
    0.28
    唪
    0.28
     někter
    0.28
     다음과
    0.27
    yelination
    0.27
    POSITIVE LOGITS
     epitome
    0.54
     most
    0.53
     easiest
    0.50
     quintessential
    0.48
     toughest
    0.47
     coolest
    0.47
     hardest
    0.46
     highest
    0.45
     clearest
    0.44
     brainchild
    0.44
    Act Density 0.414%

    No Known Activations