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

    Neuronpedia

    INDEX
    Explanations

    research reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Util
    -0.08
     tours
    -0.07
    dur
    -0.07
     замі
    -0.06
     defin
    -0.06
    .manager
    -0.06
    ior
    -0.06
     firstName
    -0.06
    .imp
    -0.06
     loc
    -0.06
    POSITIVE LOGITS
    .initState
    0.07
    SEMB
    0.06
     Anita
    0.06
    issue
    0.06
     GTX
    0.06
     العامة
    0.06
    issues
    0.06
    enary
    0.06
    Episode
    0.06
    (ball
    0.06
    Act Density 0.150%

    No Known Activations