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

    Neuronpedia

    INDEX
    Explanations

    foreign language text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gestalten
    0.69
     характер
    0.69
     preoperative
    0.68
    Properties
    0.68
     affaires
    0.68
     производ
    0.68
     Properties
    0.67
    Identity
    0.67
     Identity
    0.67
     connaissance
    0.67
    POSITIVE LOGITS
    eban
    0.83
     duż
    0.73
    mv
    0.71
    糟
    0.69
    ूड
    0.66
     लेकर
    0.66
    큰
    0.65
    oh
    0.64
    large
    0.64
     svoj
    0.63
    Act Density 0.000%

    No Known Activations