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

    Neuronpedia

    INDEX
    Explanations

    users

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foreign
    -0.07
     Magento
    -0.06
     reversing
    -0.06
    ेह
    -0.06
     Wolff
    -0.06
    redit
    -0.06
    jection
    -0.06
     Owl
    -0.06
     Jordan
    -0.06
     robotic
    -0.06
    POSITIVE LOGITS
     <>↵
    0.08
     lvl
    0.07
     }));↵↵
    0.07
    =!
    0.07
    .des
    0.07
    .BOTTOM
    0.07
    _lo
    0.07
    Чтобы
    0.07
     �
    0.06
    ]interface
    0.06
    Act Density 0.008%

    No Known Activations