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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cohol
    -0.07
    ues
    -0.07
     Пред
    -0.07
     mer
    -0.07
    Link
    -0.07
    령
    -0.07
    に対
    -0.06
     Raven
    -0.06
    macen
    -0.06
     Crime
    -0.06
    POSITIVE LOGITS
     namespace
    0.07
    NotFoundError
    0.06
     Karnataka
    0.06
    сторія
    0.06
     buurt
    0.06
    osg
    0.06
     >&
    0.06
    cors
    0.06
     خاطر
    0.06
    622
    0.06
    Act Density 0.000%

    No Known Activations