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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]}"↵
    -0.06
    ']);
↵
    -0.06
     }

↵
    -0.06
    ансов
    -0.06
     будинку
    -0.06
    ':''
    -0.06
    PIO
    -0.06
     borderWidth
    -0.06
    "},
↵
    -0.06
    摸
    -0.06
    POSITIVE LOGITS
    ר
    0.07
    obile
    0.07
     outlets
    0.07
     longer
    0.07
    ован
    0.07
    ean
    0.07
    iston
    0.07
    Buffer
    0.07
     incorporating
    0.06
     sequentially
    0.06
    Act Density 0.000%

    No Known Activations