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

    Neuronpedia

    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tibetan
    -0.07
    -members
    -0.07
     nerd
    -0.07
     SEXP
    -0.06
     chuyến
    -0.06
    pas
    -0.06
    cimiento
    -0.06
     closets
    -0.06
    lname
    -0.06
     Pager
    -0.06
    POSITIVE LOGITS
    ,_
    0.06
     Raum
    0.06
    한테
    0.06
     Assass
    0.06
    **,
    0.06
     punishment
    0.06
    annel
    0.06
    ừng
    0.06
    alties
    0.06
     handful
    0.06
    Act Density 0.056%

    No Known Activations