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

    Neuronpedia

    INDEX
    Explanations

    say "print"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     difficulties
    -0.07
     ş
    -0.07
     impose
    -0.07
     perspective
    -0.06
     dangers
    -0.06
     Ary
    -0.06
     Hide
    -0.06
     thats
    -0.06
     Nil
    -0.06
    scanf
    -0.06
    POSITIVE LOGITS
    πτυ
    0.08
    _longitude
    0.07
    ká
    0.07
    .surface
    0.06
    ню
    0.06
     навк
    0.06
    Vu
    0.06
     �
    0.06
    �ng
    0.06
    (LL
    0.06
    Act Density 0.010%

    No Known Activations