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

    Neuronpedia

    INDEX
    Explanations

    say keyboard keys

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    neutral
    -0.07
     Nights
    -0.07
    ательно
    -0.07
    714
    -0.07
    Expr
    -0.06
     Quebec
    -0.06
     starter
    -0.06
     dostate
    -0.06
     expense
    -0.06
    альну
    -0.06
    POSITIVE LOGITS
    送料無料
    0.07
     AssemblyDescription
    0.06
     isize
    0.06
    unistd
    0.06
    ��
    0.06
    =root
    0.06
    、
    0.06
     probl
    0.06
    Comparable
    0.06
    適
    0.06
    Act Density 0.044%

    No Known Activations