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

    Neuronpedia

    INDEX
    Explanations

    abstraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alted
    -0.07
     etme
    -0.07
    -On
    -0.06
     blame
    -0.06
    xbc
    -0.06
     favourable
    -0.06
     spoke
    -0.06
     生
    -0.06
    аль
    -0.06
     الثانية
    -0.06
    POSITIVE LOGITS
    '].
    0.06
    (conf
    0.06
    trieve
    0.06
     );↵↵↵
    0.06
    _RPC
    0.06
     correspondent
    0.06
     unsigned
    0.06
     اینتر
    0.06
    					↵
    0.06
    ...');↵
    0.06
    Act Density 0.095%

    No Known Activations