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

    Neuronpedia

    INDEX
    Explanations

    update code or rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     рішення
    0.42
    镐
    0.39
     அவ்
    0.38
    亮相
    0.38
    这不是
    0.37
     सलूशन
    0.37
    честве
    0.37
     fiancée
    0.37
     విధంగా
    0.37
     hizmet
    0.37
    POSITIVE LOGITS
     criterios
    0.42
    ::-
    0.42
    reel
    0.37
     reel
    0.34
    žka
    0.34
    änk
    0.34
    álie
    0.34
    anker
    0.33
     gates
    0.33
    atical
    0.33
    Act Density 0.000%

    No Known Activations