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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     orally
    -0.07
    _weak
    -0.07
    .junit
    -0.07
     contacts
    -0.07
    .cards
    -0.06
    “For
    -0.06
     Mac
    -0.06
    (columns
    -0.06
    quisites
    -0.06
     filmpjes
    -0.06
    POSITIVE LOGITS
    478
    0.06
    upert
    0.06
    .';↵
    0.06
     Vě
    0.06
     �
    0.06
     pardon
    0.06
    로그
    0.06
    generation
    0.06
     fost
    0.06
    ὴ
    0.06
    Act Density 0.045%

    No Known Activations