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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aduras
    0.58
     коман
    0.58
     right
    0.57
    有
    0.57
     HAVING
    0.57
     vun
    0.56
    Thats
    0.56
     DON
    0.55
    DON
    0.55
     Vino
    0.54
    POSITIVE LOGITS
     !,
    0.58
     please
    0.52
    let
    0.50
    "),
    0.49
     воспринима
    0.49
     note
    0.48
     />,
    0.48
     ।,
    0.47
    unakan
    0.47
    :",
    0.47
    Act Density 0.256%

    No Known Activations