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

    Neuronpedia

    INDEX
    Explanations

    DeepMind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carénés
    0.47
     바꾸
    0.45
     verhind
    0.45
     ivvu
    0.45
     SHALL
    0.44
     DAMAGE
    0.43
     prépuce
    0.43
     attham
    0.43
     proizvođa
    0.43
    <unused1113>
    0.42
    POSITIVE LOGITS
    ;
    0.52
    <
    0.47
     May
    0.46
    ology
    0.45
    %
    0.45
    +
    0.44
    }
    0.44
    >
    0.43
    {
    0.43
    [
    0.43
    Act Density 0.021%

    No Known Activations