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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ould
    -0.07
    Rad
    -0.07
    vey
    -0.07
     Rad
    -0.07
    tax
    -0.06
     арх
    -0.06
    model
    -0.06
     columns
    -0.06
     pent
    -0.06
     rằng
    -0.06
    POSITIVE LOGITS
    Skin
    0.07
    |)↵
    0.07
     ışı
    0.06
    ับส
    0.06
    Possible
    0.06
     Nuggets
    0.06
     Tickets
    0.06
     doğr
    0.06
     해결
    0.06
    umblr
    0.06
    Act Density 0.030%

    No Known Activations