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

    Neuronpedia

    INDEX
    Explanations

    contribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATEST
    -0.07
     sett
    -0.07
    适应
    -0.06
    _LARGE
    -0.06
     kc
    -0.06
    开头
    -0.06
     fortunately
    -0.06
    休
    -0.06
     selector
    -0.06
    elic
    -0.06
    POSITIVE LOGITS
     vaz
    0.08
     profits
    0.07
    心目
    0.07
    times
    0.07
     scans
    0.07
    oxid
    0.07
    }$/
    0.07
    矻
    0.07
    éal
    0.07
     Courts
    0.06
    Act Density 0.010%

    No Known Activations