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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ัญห
    -0.07
    programs
    -0.07
    Allows
    -0.07
     interest
    -0.07
     sizes
    -0.07
     shapes
    -0.06
     всей
    -0.06
    Ball
    -0.06
     CURRENT
    -0.06
     Digit
    -0.06
    POSITIVE LOGITS
     Flam
    0.06
    )").
    0.06
    ival
    0.06
     emoc
    0.06
    uyền
    0.06
     McLaren
    0.06
    ustainability
    0.06
    .Sub
    0.06
    ........................
    0.06
     povin
    0.06
    Act Density 0.004%

    No Known Activations