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

    Neuronpedia

    INDEX
    Explanations

    weather and physical objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ke
    0.46
    P
    0.46
    T
    0.45
    D
    0.43
     Pend
    0.43
    TIA
    0.42
    KE
    0.42
    การ
    0.42
    のア
    0.41
    KA
    0.40
    POSITIVE LOGITS
     CORPER
    0.56
     asientos
    0.49
    remos
    0.49
     raindrops
    0.48
    indows
    0.48
    clientes
    0.47
     ingest
    0.47
    делить
    0.47
    remo
    0.46
     primers
    0.46
    Act Density 0.001%

    No Known Activations