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

    Neuronpedia

    INDEX
    Explanations

    shapes and historical facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rün
    0.48
    ها
    0.48
    يو
    0.46
    يا
    0.46
    }\
    0.46
    rece
    0.44
    çu
    0.44
    ̧
    0.44
    ç
    0.44
    }
    0.43
    POSITIVE LOGITS
     продол
    0.50
     auffi
    0.49
    一張
    0.47
     entitles
    0.46
    矯正
    0.46
     debts
    0.45
    ይም
    0.45
     అందుకే
    0.45
     করিবে
    0.45
     counterv
    0.45
    Act Density 0.002%

    No Known Activations