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

    Neuronpedia

    INDEX
    Explanations

    127

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     flour
    -0.07
     Administration
    -0.07
    ARIO
    -0.07
     nord
    -0.07
     Beled
    -0.07
    arc
    -0.07
     password
    -0.07
     kø
    -0.06
     Cod
    -0.06
    mada
    -0.06
    POSITIVE LOGITS
    127
    0.10
     </>↵
    0.06
    "/>↵
    0.06
    ΕΝ
    0.06
    prm
    0.06
    उत
    0.06
    ，还
    0.06
    argument
    0.06
    ")));
↵
    0.06
    WithOptions
    0.06
    Act Density 0.001%

    No Known Activations