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

    Neuronpedia

    INDEX
    Explanations

    design, cause, or data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഉണ്ട്
    0.54
     uporab
    0.51
     fabricante
    0.49
     infix
    0.48
     utilisant
    0.48
     atribu
    0.47
     ladr
    0.46
     souten
    0.46
     contribu
    0.46
     étend
    0.45
    POSITIVE LOGITS
    ajos
    0.47
    igh
    0.46
    soldiers
    0.43
    ellas
    0.43
    awas
    0.42
    ental
    0.41
    gies
    0.41
    粒子
    0.41
    ael
    0.40
    ic
    0.40
    Act Density 0.004%

    No Known Activations