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

    Neuronpedia

    INDEX
    Explanations

    legal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Listening
    -0.07
    итуа
    -0.06
    Capability
    -0.06
    avascript
    -0.06
     munch
    -0.06
     dressed
    -0.06
    Science
    -0.06
    istic
    -0.06
     midfielder
    -0.06
    POSITIVE LOGITS
     rivals
    0.08
    上海
    0.06
     ран
    0.06
    nder
    0.06
    (req
    0.06
     CString
    0.06
     temples
    0.06
    _Com
    0.06
    했던
    0.06
     الشر
    0.06
    Act Density 0.027%

    No Known Activations