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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    书
    -0.07
    ань
    -0.06
    ，用
    -0.06
    已
    -0.06
     Injection
    -0.06
    ICES
    -0.06
    ({'
    -0.06
     POLIT
    -0.06
    險
    -0.06
    _tC
    -0.06
    POSITIVE LOGITS
    ]}
    0.07
     relational
    0.07
     peasants
    0.07
     squir
    0.06
    DA
    0.06
    .actual
    0.06
     digestive
    0.06
     CCT
    0.06
    da
    0.06
    ليم
    0.06
    Act Density 0.044%

    No Known Activations