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

    Neuronpedia

    INDEX
    Explanations

    vertex attribute buffer locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mouseY
    0.38
    بال
    0.35
    栊
    0.33
    贿
    0.33
    Employee
    0.32
     Civilian
    0.32
    பிர
    0.32
    Empty
    0.31
    淵
    0.31
    ChangeListener
    0.31
    POSITIVE LOGITS
    Attrib
    0.48
    verifier
    0.44
    attrib
    0.40
     punkt
    0.39
    ើញ
    0.39
    uesto
    0.38
     extensión
    0.38
     indef
    0.38
    失效
    0.38
     непре
    0.37
    Act Density 0.002%

    No Known Activations