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
    בני
    -0.07
    \Requests
    -0.07
     inverse
    -0.06
    świadczenie
    -0.06
    /vnd
    -0.06
    HEMA
    -0.06
    design
    -0.06
    -products
    -0.06
     caul
    -0.06
    .GUI
    -0.06
    POSITIVE LOGITS
    arrera
    0.07
     ardından
    0.07
    見え
    0.07
     day
    0.07
     wybra
    0.07
     separated
    0.07
     있었
    0.06
    ちなみ
    0.06
    鹰
    0.06
    放弃
    0.06
    Act Density 0.009%

    No Known Activations