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

    Neuronpedia

    INDEX
    Explanations

    death penalty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    VERAGE
    -0.07
     fuzz
    -0.06
    buz
    -0.06
     analyzing
    -0.06
    izens
    -0.06
    VERSE
    -0.06
    ZONE
    -0.06
    itory
    -0.06
     Comb
    -0.06
     Traverse
    -0.06
    POSITIVE LOGITS
     αρι
    0.07
     poll
    0.06
    -office
    0.06
     này
    0.06
    incer
    0.06
    >')↵
    0.06
     unnamed
    0.06
     unrealistic
    0.06
    ivid
    0.06
    AFX
    0.06
    Act Density 0.028%

    No Known Activations