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

    Neuronpedia

    INDEX
    Explanations

    HM

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unce
    -0.07
     pensions
    -0.07
    temps
    -0.07
    uC
    -0.07
    venience
    -0.07
     השימוש
    -0.07
    изма
    -0.07
    ük
    -0.07
     phí
    -0.06
     מתחיל
    -0.06
    POSITIVE LOGITS
    ighb
    0.07
     boutique
    0.07
    กด
    0.07
    桃花
    0.06
     CRE
    0.06
    Broad
    0.06
    //----------------
    0.06
     Skywalker
    0.06
    0.06
    Appro
    0.06
    Act Density 0.313%

    No Known Activations