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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Shift
    -0.07
     }↵↵↵↵↵
    -0.07
     htonl
    -0.07
    opers
    -0.06
    -ups
    -0.06
     handicap
    -0.06
     ull
    -0.06
     Davidson
    -0.06
     Palmer
    -0.06
     Minds
    -0.06
    POSITIVE LOGITS
     фах
    0.06
     Etsy
    0.06
     referencing
    0.06
     prostitutas
    0.06
     Brom
    0.06
    (&:
    0.06
     cơm
    0.06
    .SqlClient
    0.06
     Dabei
    0.06
    ΟΔ
    0.06
    Act Density 0.016%

    No Known Activations