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

    Neuronpedia

    INDEX
    Explanations

    6 months passport validity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    欷
    0.42
     রহমানকে
    0.39
    辛
    0.39
    Desktop
    0.39
    产生了
    0.38
    Repe
    0.37
    Failed
    0.37
    銷售
    0.37
    筋肉
    0.36
    ónica
    0.36
    POSITIVE LOGITS
     validity
    0.65
     Validity
    0.62
     passport
    0.57
     valid
    0.55
    valid
    0.54
     passports
    0.52
    Validity
    0.51
     VALID
    0.50
     gült
    0.50
     वैलिड
    0.50
    Act Density 0.005%

    No Known Activations