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

    Neuronpedia

    INDEX
    Explanations

    Multiplication by 2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     innocence
    -0.07
    ुक
    -0.06
     Pollution
    -0.06
     esto
    -0.06
     그리
    -0.06
     climax
    -0.06
     auss
    -0.06
    ,test
    -0.06
    ection
    -0.06
    `)
    -0.06
    POSITIVE LOGITS
    ...↵↵↵
    0.06
    pliers
    0.06
     Rim
    0.06
    928
    0.06
    (Msg
    0.06
     Sebastian
    0.06
     _("
    0.06
    .calculate
    0.06
    667
    0.06
     Ан
    0.06
    Act Density 0.015%

    No Known Activations