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

    Neuronpedia

    INDEX
    Explanations

    engaging content and marketing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cứu
    1.94
     veer
    1.92
     manfaat
    1.89
     potrzeby
    1.86
    }$).
    1.85
     namanya
    1.84
     Chloride
    1.84
    럿
    1.83
     ongel
    1.82
     naf
    1.78
    POSITIVE LOGITS
    an
    1.94
    की
    1.81
    al
    1.76
    𝐚
    1.75
    𝐋
    1.69
    त
    1.67
    ain
    1.66
    a
    1.64
    𝐱
    1.61
    𝐓
    1.55
    Act Density 0.000%

    No Known Activations