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

    Neuronpedia

    INDEX
    Explanations

    transform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    材
    -0.08
     Watches
    -0.07
    avin
    -0.07
    都能
    -0.07
    张扬
    -0.07
    煓
    -0.06
     journée
    -0.06
     Jungle
    -0.06
    ust
    -0.06
    高楼
    -0.06
    POSITIVE LOGITS
    -na
    0.07
     hoş
    0.07
    插座
    0.07
     backButton
    0.07
     useful
    0.07
    userid
    0.07
    .sessions
    0.07
    0.07
     @"
    0.07
    imentary
    0.07
    Act Density 0.003%

    No Known Activations