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

    Neuronpedia

    INDEX
    Explanations

    Phone numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plymouth
    -0.07
    Authenticated
    -0.06
     Phòng
    -0.06
    dfs
    -0.06
    ्पर
    -0.06
    .gray
    -0.06
    omik
    -0.06
    427
    -0.06
    дан
    -0.06
    mitters
    -0.06
    POSITIVE LOGITS
     determines
    0.08
     Generated
    0.06
     адміністра
    0.06
    (Result
    0.06
     в
    0.06
     implication
    0.06
     scenery
    0.06
     neither
    0.06
    주의
    0.06
     happened
    0.06
    Act Density 0.005%

    No Known Activations