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

    Neuronpedia

    INDEX
    Explanations

    software descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /+
    -0.07
    IGNORE
    -0.07
    ertext
    -0.07
    ều
    -0.07
    �
    -0.07
    篝
    -0.07
    �
    -0.06
     downt
    -0.06
    <class
    -0.06
    血管
    -0.06
    POSITIVE LOGITS
    ания
    0.08
    שית
    0.07
     stockholm
    0.07
    xxx
    0.07
    ᕗ
    0.07
    」「
    0.07
    ность
    0.07
    istorical
    0.07
     glass
    0.07
     налогов
    0.07
    Act Density 0.015%

    No Known Activations