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

    Neuronpedia

    INDEX
    Explanations

    aw

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    орт
    -0.07
     pathways
    -0.07
    projects
    -0.07
     pathway
    -0.06
     NUM
    -0.06
    processing
    -0.06
    $c
    -0.06
     stress
    -0.06
     proxies
    -0.06
    being
    -0.06
    POSITIVE LOGITS
     Liber
    0.07
     اجرای
    0.07
     پژ
    0.07
     Ai
    0.07
     Απ
    0.06
     lòng
    0.06
     Uns
    0.06
     görev
    0.06
    拥有
    0.06
     Noon
    0.06
    Act Density 0.002%

    No Known Activations