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

    Neuronpedia

    INDEX
    Explanations

    AI researchers, Vicuna, scientists, traditional computing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.60
    od
    0.54
    ER
    0.52
    ah
    0.51
     друг
    0.50
    im
    0.48
    as
    0.48
    ot
    0.47
     Перед
    0.47
    agal
    0.47
    POSITIVE LOGITS
    、
    0.52
     artistes
    0.48
     entertained
    0.47
    。(
    0.47
    ፣
    0.47
    ၊
    0.45
    经常
    0.44
    胆
    0.44
    ３
    0.42
     bothered
    0.42
    Act Density 0.001%

    No Known Activations