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

    Neuronpedia

    INDEX
    Explanations

    . ) fuels chickens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.49
    ):
    0.49
    );*/
    0.46
    ()){
    0.45
    ↵↵↵↵
    0.43
    .):
    0.43
    *:
    0.43
    ()):
    0.42
    ちなみに
    0.42
    ){
    0.41
    POSITIVE LOGITS
    ⑵
    0.42
     ii
    0.38
    ⏎
    0.38
    
    0.37
    ;
    0.37
    ;')
    0.36
    ;.
    0.35
    0.34
    arlings
    0.34
     ;$
    0.33
    Act Density 0.271%

    No Known Activations