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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eczy
    -0.08
    -plane
    -0.07
    을
    -0.07
    تاب
    -0.07
    ñas
    -0.07
    ancia
    -0.07
    卷
    -0.07
    lessness
    -0.07
    uess
    -0.06
     اصول
    -0.06
    POSITIVE LOGITS
    ximity
    0.06
     WP
    0.06
     imageURL
    0.06
    ２
    0.06
     WW
    0.06
     Kg
    0.06
     analytical
    0.06
    .dy
    0.06
     direccion
    0.06
     gson
    0.06
    Act Density 0.001%

    No Known Activations