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

    Neuronpedia

    INDEX
    Explanations

    tables and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    шкой
    0.47
    غراف
    0.46
     mandate
    0.46
    गाह
    0.45
    áciu
    0.45
     stipulates
    0.45
     marred
    0.44
     unruly
    0.44
     negotiators
    0.44
    ים
    0.44
    POSITIVE LOGITS
    ---|
    0.98
    -|
    0.73
    +|
    0.71
     |
    0.71
    .|
    0.67
       
    0.65
    0.64
    |
    0.63
    }|
    0.61
              
    0.60
    Act Density 0.090%

    No Known Activations