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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     가까
    -0.08
    Grade
    -0.06
     fortunes
    -0.06
     iframe
    -0.06
    _tracker
    -0.06
    とした
    -0.06
     совершенно
    -0.06
    cant
    -0.06
     زنی
    -0.06
    /users
    -0.06
    POSITIVE LOGITS
    Part
    0.07
     multipart
    0.07
     발
    0.06
    _POINTS
    0.06
     ALT
    0.06
     Phoenix
    0.06
    _MAC
    0.06
    ervatives
    0.06
    _AVAILABLE
    0.06
    tility
    0.06
    Act Density 0.000%

    No Known Activations