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

    Neuronpedia

    INDEX
    Explanations

    reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brake
    0.42
    Simpson
    0.41
    No
    0.40
     Simpson
    0.40
    ండా
    0.39
     disappointment
    0.38
    ర్‌లో
    0.37
    eh
    0.37
    atisf
    0.36
    Nicola
    0.36
    POSITIVE LOGITS
     reference
    0.73
     참고
    0.73
     references
    0.68
     referencia
    0.68
    参考に
    0.67
    参考
    0.66
     referência
    0.66
    參考
    0.62
     Reference
    0.62
     riferimento
    0.61
    Act Density 0.007%

    No Known Activations