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

    Neuronpedia

    INDEX
    Explanations

    possessive, contractions, and "is"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    moved
    -0.06
     weakening
    -0.06
    “You
    -0.06
    ='.
    -0.06
     xi
    -0.06
    ’all
    -0.06
     predictor
    -0.06
     Walking
    -0.06
    VICE
    -0.06
    checkout
    -0.06
    POSITIVE LOGITS
     якої
    0.08
    _REL
    0.07
     ruta
    0.07
    ابل
    0.07
    prus
    0.06
    าประ
    0.06
     nj
    0.06
    _country
    0.06
    .ribbon
    0.06
    (""))↵
    0.06
    Act Density 0.140%

    No Known Activations