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

    Neuronpedia

    INDEX
    Explanations

    algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comic
    -0.07
    -gun
    -0.07
     expose
    -0.07
     tough
    -0.07
     StyleSheet
    -0.06
    TEAM
    -0.06
     Senator
    -0.06
     Thompson
    -0.06
     багатьох
    -0.06
    ショ
    -0.06
    POSITIVE LOGITS
    .the
    0.07
    (enc
    0.07
     engineered
    0.07
    pcl
    0.06
    /filepath
    0.06
    _GAP
    0.06
     Sanity
    0.06
    .RESET
    0.06
     "!
    0.06
     |_
    0.06
    Act Density 0.091%

    No Known Activations