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

    Neuronpedia

    INDEX
    Explanations

    state of the game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cifras
    0.40
     streets
    0.39
     mood
    0.38
     Minus
    0.38
    جز
    0.38
     grieve
    0.37
    ጣት
    0.37
    streets
    0.37
     versucht
    0.36
     wonder
    0.36
    POSITIVE LOGITS
    প্লে
    0.42
     হবার
    0.41
     nè
    0.40
     eten
    0.40
    selected
    0.39
    Defaults
    0.39
     অন্যায়
    0.39
     янва
    0.39
    Complement
    0.38
     নহে
    0.38
    Act Density 0.000%

    No Known Activations