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

    Neuronpedia

    INDEX
    Explanations

    Audience, supreme, third, gameplay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zeus
    0.44
    g
    0.43
     Genesis
    0.41
    ang
    0.41
    0.40
    胜
    0.40
     през
    0.39
    ogonal
    0.39
     Pilates
    0.39
    ⑩
    0.39
    POSITIVE LOGITS
     farlo
    0.47
    ES
    0.47
    Jackie
    0.45
     Aby
    0.44
    တ်
    0.44
     ouvrir
    0.44
    стру
    0.44
    ച്ചി
    0.44
    द्दीन
    0.43
    Cho
    0.43
    Act Density 0.002%

    No Known Activations