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

    Neuronpedia

    INDEX
    Explanations

    bonus deficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     odgov
    0.64
    ндә
    0.63
    đồng
    0.62
    мили
    0.61
    <0x0D>
    0.59
    ný
    0.59
    nilai
    0.59
    tragung
    0.59
     a
    0.59
    да
    0.58
    POSITIVE LOGITS
    0.68
    is
    0.66
     Drury
    0.57
     juncture
    0.57
     Polytechnic
    0.56
     Connell
    0.55
     Cook
    0.55
     Hernandez
    0.55
     Streets
    0.54
     انتشار
    0.54
    Act Density 0.000%

    No Known Activations