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

    Neuronpedia

    INDEX
    Explanations

    description, data, parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.57
    dll
    0.53
     количе
    0.50
    ack
    0.49
    umar
    0.49
    ión
    0.49
    aciones
    0.49
    órico
    0.48
    ’
    0.48
    iesel
    0.47
    POSITIVE LOGITS
    א
    0.48
    ա
    0.48
    准
    0.48
    ע
    0.46
     yada
    0.46
    生
    0.46
    面的
    0.46
    面
    0.46
    ק
    0.45
    الن
    0.44
    Act Density 0.000%

    No Known Activations