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

    Neuronpedia

    INDEX
    Explanations

    Kingdom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     baker
    -0.07
    PO
    -0.07
     resistance
    -0.06
     slot
    -0.06
     Fair
    -0.06
    ATOR
    -0.06
    7
    -0.06
     Examples
    -0.06
    cade
    -0.06
     war
    -0.06
    POSITIVE LOGITS
    '},
↵
    0.08
    )[:
    0.07
     dří
    0.07
     /*
↵
    0.07
    '},↵
    0.07
    //#
    0.06
    ,ev
    0.06
     καλύ
    0.06
    Sau
    0.06
    (diff
    0.06
    Act Density 0.023%

    No Known Activations