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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .PageSize
    -0.08
    _MC
    -0.06
    =m
    -0.06
    √
    -0.06
     حر
    -0.06
    نسا
    -0.06
    ाइल
    -0.06
    ưỡng
    -0.06
     이유
    -0.06
    _vect
    -0.06
    POSITIVE LOGITS
    code
    0.07
    Code
    0.07
    decoded
    0.07
    Media
    0.06
     Comedy
    0.06
     programmer
    0.06
     Tweet
    0.06
    TY
    0.06
     Naz
    0.06
    Definition
    0.06
    Act Density 0.005%

    No Known Activations