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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     możli
    -0.07
    ))↵↵
    -0.06
    maze
    -0.06
     revolver
    -0.06
    ітет
    -0.06
    });↵↵↵
    -0.06
    МО
    -0.06
     �
    -0.06
    ])↵↵↵
    -0.06
     ¥
    -0.06
    POSITIVE LOGITS
    /perl
    0.08
     metals
    0.07
     dedicated
    0.07
     Wireless
    0.07
    _occ
    0.07
    อเมร
    0.06
    -dominated
    0.06
     Kang
    0.06
     Ellison
    0.06
    -console
    0.06
    Act Density 0.105%

    No Known Activations