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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }])↵
    -0.07
    자를
    -0.07
    ]},↵
    -0.06
    งม
    -0.06
    め
    -0.06
    いに
    -0.06
    <byte
    -0.06
    _In
    -0.06
    onomies
    -0.06
    ereço
    -0.06
    POSITIVE LOGITS
    TEST
    0.07
    _prime
    0.07
     Efficiency
    0.07
     negot
    0.06
     
    0.06
     Politico
    0.06
    mlx
    0.06
    _SEC
    0.06
    removeClass
    0.06
    ATIC
    0.06
    Act Density 0.013%

    No Known Activations