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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tablename
    -0.06
    _basename
    -0.06
     arteries
    -0.06
    �
    -0.06
     Βασ
    -0.06
    .Point
    -0.06
    _prep
    -0.06
    太
    -0.06
    _original
    -0.06
     이러한
    -0.06
    POSITIVE LOGITS
    uels
    0.07
    &↵
    0.07
    ")
↵
↵
    0.07
    astes
    0.07
     cw
    0.06
    ]],↵
    0.06
     Pirates
    0.06
    }/
    0.06
     '\\
    0.06
    }->
    0.06
    Act Density 0.048%

    No Known Activations