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

    Neuronpedia

    INDEX
    Explanations

    title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ayet
    -0.07
    แ
    -0.07
     존
    -0.07
    рес
    -0.07
    rava
    -0.07
    Ball
    -0.06
    ivot
    -0.06
     Drupal
    -0.06
    iglia
    -0.06
    written
    -0.06
    POSITIVE LOGITS
     يوم
    0.07
     dung
    0.06
     зда
    0.06
     usher
    0.06
     соп
    0.06
    Local
    0.06
    дается
    0.06
    戻
    0.06
     Overview
    0.06
    ۰۰۰
    0.06
    Act Density 0.005%

    No Known Activations