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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guidelines
    -0.06
    manual
    -0.06
     unarmed
    -0.06
    ابق
    -0.06
    一个
    -0.06
    альным
    -0.06
    Kids
    -0.06
    chang
    -0.06
    approx
    -0.06
    .COLUMN
    -0.06
    POSITIVE LOGITS
    ]:↵↵↵
    0.07
     그를
    0.07
     flask
    0.07
    .");
↵
    0.07
     관련
    0.07
    ([])↵
    0.06
     рецепт
    0.06
     largo
    0.06
     Zend
    0.06
    '])
↵
    0.06
    Act Density 0.007%

    No Known Activations