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

    Neuronpedia

    INDEX
    Explanations

    additional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lazar
    -0.07
    _Buffer
    -0.07
    JKLMNOP
    -0.07
    来的
    -0.06
    JR
    -0.06
    alardan
    -0.06
     صاد
    -0.06
     cục
    -0.06
    ],'
    -0.06
     tik
    -0.06
    POSITIVE LOGITS
    itious
    0.07
     compliments
    0.06
     special
    0.06
     ghost
    0.06
     no
    0.06
     Enhanced
    0.06
     голос
    0.06
     секрет
    0.06
    tp
    0.06
     here
    0.06
    Act Density 0.004%

    No Known Activations