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

    Neuronpedia

    INDEX
    Explanations

    higher

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    цией
    -0.08
     boat
    -0.07
    IZ
    -0.07
     boats
    -0.06
    γράφ
    -0.06
    capitalize
    -0.06
     Thomas
    -0.06
     pandas
    -0.06
    Thomas
    -0.06
    ]):
↵
    -0.06
    POSITIVE LOGITS
    (cor
    0.07
    भग
    0.07
    �
    0.07
     leve
    0.06
    Rus
    0.06
    condition
    0.06
     Mater
    0.06
    currency
    0.06
    fet
    0.06
    ||(
    0.06
    Act Density 0.007%

    No Known Activations