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

    Neuronpedia

    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    σμού
    -0.07
    елей
    -0.06
     Paradise
    -0.06
     STOCK
    -0.06
    -keys
    -0.06
    _FINAL
    -0.06
     coffin
    -0.06
    .total
    -0.06
    bing
    -0.06
    نين
    -0.06
    POSITIVE LOGITS
    (sess
    0.07
    clidean
    0.06
    ()));
↵
    0.06
     ${↵
    0.06
     Instances
    0.06
    };
↵
    0.06
     blond
    0.06
    .configureTestingModule
    0.06
     الملك
    0.06
     endforeach
    0.06
    Act Density 0.022%

    No Known Activations