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

    Neuronpedia

    INDEX
    Explanations

    parentheses/brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fourth
    -0.06
    toolbox
    -0.06
    iyah
    -0.06
    ющ
    -0.06
    rapid
    -0.06
     Domestic
    -0.06
     visibly
    -0.06
    적으로
    -0.06
    -quarters
    -0.06
    álně
    -0.06
    POSITIVE LOGITS
     thân
    0.07
     Subcommittee
    0.07
    征
    0.07
    (entry
    0.06
    essoa
    0.06
    的心
    0.06
     hearings
    0.06
     Mines
    0.06
     forbidden
    0.06
     fiss
    0.06
    Act Density 0.016%

    No Known Activations