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

    Neuronpedia

    INDEX
    Explanations

    abstract thought, self-awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Elaina
    0.59
    ക്കേണ്ട
    0.52
    ৰ
    0.50
    ⃙
    0.48
     Secondo
    0.48
     Hinweise
    0.47
     sez
    0.46
    จาก
    0.46
     disque
    0.45
    瘤
    0.45
    POSITIVE LOGITS
    OMO
    0.46
    AN
    0.45
    WY
    0.42
    Appeal
    0.41
    P
    0.40
     facilities
    0.40
    Facilities
    0.40
    čiai
    0.40
    AT
    0.39
    J
    0.39
    Act Density 0.000%

    No Known Activations