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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FirstOrDefault
    -0.07
     FAIL
    -0.07
     修
    -0.07
    Except
    -0.06
    prototype
    -0.06
    .Ad
    -0.06
    .Type
    -0.06
    archivo
    -0.06
    -outs
    -0.06
     daß
    -0.06
    POSITIVE LOGITS
    membership
    0.07
    erguson
    0.07
    )")↵↵
    0.06
     keywords
    0.06
    ↵
    0.06
     holland
    0.06
    orton
    0.06
     prescription
    0.06
     motivations
    0.06
    ";↵↵
    0.06
    Act Density 0.018%

    No Known Activations