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

    Neuronpedia

    INDEX
    Explanations

    not the cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nu
    0.46
     nama
    0.43
     behandling
    0.43
     treatment
    0.42
     trattamento
    0.42
     +(
    0.41
     nome
    0.40
     xung
    0.40
     phúc
    0.40
    กก
    0.40
    POSITIVE LOGITS
    ঙ্গার
    0.49
    нец
    0.47
     I
    0.47
     herself
    0.47
    oten
    0.47
     Compared
    0.46
    වාස
    0.46
     Perhaps
    0.45
    ん
    0.45
     Trucks
    0.45
    Act Density 0.001%

    No Known Activations