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

    Neuronpedia

    INDEX
    Explanations

    introductions to concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ক
    0.89
    往往
    0.85
     மற்றும்
    0.85
     경우는
    0.84
     Каждый
    0.83
    ב
    0.83
     가
    0.82
    และ
    0.82
     doesn
    0.82
     လ
    0.81
    POSITIVE LOGITS
    ванням
    0.93
    ,
    0.91
     eponymous
    0.87
    un
    0.82
    atrice
    0.80
     ABO
    0.80
    featuring
    0.80
    plication
    0.79
    HLIGHT
    0.78
    speople
    0.77
    Act Density 0.297%

    No Known Activations