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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Na
    -0.06
    .to
    -0.06
    .Code
    -0.06
     cs
    -0.06
     Unblock
    -0.06
    SCP
    -0.05
     Het
    -0.05
    -ons
    -0.05
     Gwen
    -0.05
     Manifest
    -0.05
    POSITIVE LOGITS
     почина
    0.07
    Published
    0.07
     brightness
    0.07
     scramble
    0.07
     hran
    0.06
     δεν
    0.06
    лот
    0.06
     налог
    0.06
    :relative
    0.06
     sä
    0.06
    Act Density 0.003%

    No Known Activations