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

    Neuronpedia

    INDEX
    Explanations

    detailed description until

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ምን
    0.51
     Voltage
    0.50
     spur
    0.50
     совокуп
    0.50
     cardinality
    0.49
    韜
    0.49
     weist
    0.49
     Dali
    0.49
     どう
    0.48
     国
    0.47
    POSITIVE LOGITS
    '
    0.54
    kan
    0.52
    ৯
    0.52
    hme
    0.51
    :'
    0.50
    larını
    0.49
    ماً
    0.49
    can
    0.48
    owe
    0.48
    项目
    0.48
    Act Density 0.000%

    No Known Activations