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

    Neuronpedia

    INDEX
    Explanations

    we statement of action or intent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্স
    0.59
    被
    0.51
    b
    0.51
    的
    0.51
    GetMapping
    0.50
    Menus
    0.49
    는데
    0.48
    （
    0.48
    Buttons
    0.47
    「
    0.47
    POSITIVE LOGITS
     ourselves
    0.85
    ad
    0.66
     هستیم
    0.64
     хотим
    0.61
    ان
    0.60
    artigen
    0.60
     можем
    0.59
     utilisons
    0.59
     છીએ
    0.58
    iliśmy
    0.57
    Act Density 0.410%

    No Known Activations