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

    Neuronpedia

    INDEX
    Explanations

    attributing roles and worthiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ד
    0.61
    вата
    0.57
    िड
    0.52
    s
    0.52
    ן
    0.52
    וד
    0.51
    ਲ
    0.51
    ל
    0.50
    ین
    0.50
    ע
    0.50
    POSITIVE LOGITS
     Variations
    0.57
     übernommen
    0.52
     Estimate
    0.51
    কারী
    0.50
     Meh
    0.49
     Unser
    0.49
     Koenig
    0.48
     contempla
    0.48
     Versch
    0.47
     Andere
    0.47
    Act Density 0.000%

    No Known Activations