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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .box
    -0.07
    (t
    -0.06
    ชาว
    -0.06
     팬
    -0.06
    �
    -0.06
    overview
    -0.06
    .tipo
    -0.06
    filme
    -0.06
     cơm
    -0.06
    Inform
    -0.06
    POSITIVE LOGITS
     partially
    0.06
    سر
    0.06
    Further
    0.06
    high
    0.06
    _YELLOW
    0.06
     Safe
    0.06
    _userid
    0.06
     neger
    0.06
    WithContext
    0.06
     uz
    0.06
    Act Density 0.043%

    No Known Activations