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

    Neuronpedia

    INDEX
    Explanations

    beta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NK
    -0.07
     remind
    -0.07
    _tx
    -0.06
     spoke
    -0.06
     volumes
    -0.06
    简洁
    -0.06
    不低于
    -0.06
     أمر
    -0.06
    (sizeof
    -0.06
    Suffix
    -0.06
    POSITIVE LOGITS
     Kab
    0.07
    桃園
    0.07
    ־
    0.07
    묠
    0.07
    ⤄
    0.06
    webElementXpaths
    0.06
     rağmen
    0.06
     Vault
    0.06
    _led
    0.06
     ducks
    0.06
    Act Density 0.001%

    No Known Activations