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

    Neuronpedia

    INDEX
    Explanations

    AUC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     V
    0.57
    sburg
    0.56
    _
    0.56
    line
    0.52
    sco
    0.52
    limit
    0.51
    ^
    0.51
    _.
    0.50
    census
    0.50
    __
    0.49
    POSITIVE LOGITS
     этом
    0.64
     AUC
    0.58
    orpion
    0.57
     இந்த
    0.56
     για
    0.55
     有
    0.55
     такими
    0.55
    ında
    0.55
     кре
    0.55
     താര
    0.53
    Act Density 0.004%

    No Known Activations