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

    Neuronpedia

    INDEX
    Explanations

    neutral alignment and metadata

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ني
    0.45
     verloren
    0.45
    ר
    0.44
    тири
    0.44
    ACS
    0.44
    mq
    0.43
    IsNullOrEmpty
    0.43
     gamut
    0.43
     kanya
    0.43
    Un
    0.42
    POSITIVE LOGITS
     τη
    0.54
    łem
    0.52
    デア
    0.51
    လီ
    0.50
     得
    0.49
     ली
    0.48
    どり
    0.48
     डैश
    0.48
    striatis
    0.48
     മികച്ച
    0.47
    Act Density 0.000%

    No Known Activations