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

    Neuronpedia

    INDEX
    Explanations

    alternative terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zM
    -0.07
    139
    -0.07
    .sat
    -0.06
    �
    -0.06
    ()'
    -0.06
     diseño
    -0.06
    	Simple
    -0.06
     हम
    -0.06
     diner
    -0.06
    Fake
    -0.06
    POSITIVE LOGITS
     Liga
    0.07
    0.07
    0.06
    ога
    0.06
     obsess
    0.06
     prevailing
    0.06
    ]):↵
    0.06
    ]↵↵
    0.06
    “.
    0.06
     içerisinde
    0.06
    Act Density 0.038%

    No Known Activations